Freeze code long context profile v6

This commit is contained in:
2026-07-24 00:52:23 +08:00
parent 89d5ebbbc0
commit b80d3f03de
60 changed files with 5353 additions and 1 deletions

View File

@@ -0,0 +1,277 @@
time_stats.attn_input_reshape.min,time_stats.attn_input_reshape.max,time_stats.attn_input_reshape.mean,time_stats.attn_input_reshape.median,time_stats.attn_input_reshape.std,time_stats.attn_kv_cache_save.min,time_stats.attn_kv_cache_save.max,time_stats.attn_kv_cache_save.mean,time_stats.attn_kv_cache_save.median,time_stats.attn_kv_cache_save.std,time_stats.attn_prefill.min,time_stats.attn_prefill.max,time_stats.attn_prefill.mean,time_stats.attn_prefill.median,time_stats.attn_prefill.std,time_stats.attn_decode.min,time_stats.attn_decode.max,time_stats.attn_decode.mean,time_stats.attn_decode.median,time_stats.attn_decode.std,time_stats.attn_output_reshape.min,time_stats.attn_output_reshape.max,time_stats.attn_output_reshape.mean,time_stats.attn_output_reshape.median,time_stats.attn_output_reshape.std,n_embd,n_q_head,n_kv_head,block_size,num_tensor_parallel_workers,max_model_len,batch_size,prefill_chunk_size,kv_cache_size,is_prefill,attention_backend,is_mixed_batch,mode,seq_lens,total_tokens,max_seq_len,min_seq_len,avg_seq_len,equal_seq_len,seq_len_variance,seq_len_std,seq_len_cv,is_chunked_prefill_sample,chunk_start_token,chunk_end_token,total_prefill_tokens,profiling_precision,model_arch,quant_signature,measurement_type,is_true_mixed_batch,prefill_seq_lens,prefill_kv_cache_sizes,decode_kv_cache_sizes,num_prefill_seqs,num_decode_seqs,decode_batch_size,total_batch_size,total_decode_tokens,decode_avg_kv_cache_size,batch_composition_ratio,batch_spec,projection_policy
0.0,0.0,0.0,0.0,0.0,0.01414399966597557,0.028863999992609024,0.019705599918961526,0.01771199982613325,0.005157200849836681,0.047968000173568726,0.07046400010585785,0.05810240097343922,0.05810240097343922,0.007477463486041561,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.04947200044989586,0.020412799902260303,0.01635199971497059,0.010107497379722417,0.046560000628232956,0.08323200047016144,0.05587520003318787,0.05587520003318787,0.011126758739503428,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.022207999601960182,0.017033600155264138,0.015312000177800655,0.002819235991970241,0.05104000121355057,0.07692799717187881,0.056396800279617305,0.056396800279617305,0.007481982178637539,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015072000212967396,0.022272000089287758,0.01706880023702979,0.01616000011563301,0.002460889579319197,0.06931199878454208,0.0838719978928566,0.07432000041007995,0.07432000041007995,0.004777766433175866,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.018592000007629395,0.028543999418616295,0.02095999978482723,0.019183999858796597,0.003198175496053494,0.12179200351238251,0.15408000349998474,0.1307712011039257,0.1307712011039257,0.00858807797538298,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.027775999158620834,0.03385600075125694,0.030131200328469276,0.029680000618100166,0.0021152558103575215,0.32678401470184326,0.3450239896774292,0.33396480381488797,0.33396480381488797,0.0045872424917606375,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04438399896025658,0.05084799975156784,0.046540799736976626,0.04531199857592583,0.002277905811237223,1.0959680080413818,1.1151360273361206,1.0999775886535645,1.0999775886535645,0.005694403246120485,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.078015998005867,0.08691199868917465,0.08114239946007729,0.08019199967384338,0.00292795706334475,4.070400238037109,4.113152027130127,4.087088012695312,4.087088012695312,0.013660567012509554,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016063999384641647,0.05167999863624573,0.022115200012922286,0.017583999782800674,0.010340094822340818,0.05196800082921982,0.09011200070381165,0.06328320093452933,0.06328320093452933,0.012557341255467452,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01583999954164028,0.026623999699950218,0.018927999772131443,0.017376000061631203,0.003514650316260619,0.06681600213050842,0.07993599772453308,0.0725280001759529,0.0725280001759529,0.004343502558613716,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01648000068962574,0.030880000442266464,0.01945280022919178,0.017967999912798405,0.004096211183007485,0.1311360001564026,0.1546880006790161,0.13908160030841826,0.13908160030841826,0.007511906874366178,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017855999991297722,0.03558399900794029,0.020851199887692927,0.018559999763965607,0.005235911594130716,0.32950401306152344,0.350271999835968,0.33912960588932034,0.33912960588932034,0.006027400986663648,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.019328000023961067,0.040608000010252,0.022790400311350822,0.020704000256955624,0.006113051965778337,1.1415679454803467,1.1518720388412476,1.144483208656311,1.144483208656311,0.0032332311374389127,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015807999297976494,0.030688000842928886,0.019596799835562707,0.01774400006979704,0.004343384771033462,0.0,0.0,0.0,0.0,0.0,0.049056001007556915,0.07580800354480743,0.05948160067200661,0.05948160067200661,0.009031541471446955,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01603199914097786,0.02486399933695793,0.01923839971423149,0.018079999834299088,0.0032282528537266424,0.0,0.0,0.0,0.0,0.0,0.05142400041222572,0.07353600114583969,0.059328000620007516,0.059328000620007516,0.0073307807735143084,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016543999314308167,0.03977600112557411,0.021379199624061585,0.018511999398469925,0.006593576176246171,0.0,0.0,0.0,0.0,0.0,0.0488319993019104,0.06435199826955795,0.05479039996862411,0.05479039996862411,0.005672522998491864,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01635199971497059,0.02844800055027008,0.019267200119793416,0.017952000722289085,0.0035068687666949577,0.0,0.0,0.0,0.0,0.0,0.049855999648571014,0.07798399776220322,0.05986879989504815,0.05986879989504815,0.01043914754878828,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016383999958634377,0.026079999282956123,0.01923519968986511,0.017791999503970146,0.0032161974331284568,0.0,0.0,0.0,0.0,0.0,0.058111999183893204,0.1045759990811348,0.06708480007946492,0.06708480007946492,0.013479022462646494,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.04057599976658821,0.019100800156593323,0.015455999877303839,0.007512281243011577,0.0,0.0,0.0,0.0,0.0,0.05363199859857559,0.07782399654388428,0.06090559959411622,0.06090559959411622,0.007544620176348091,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.02191999927163124,0.016684799920767546,0.01563199982047081,0.0024293118621811216,0.0,0.0,0.0,0.0,0.0,0.0629120022058487,0.07891199737787247,0.06891520097851753,0.06891520097851753,0.005472695665695425,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014560000039637089,0.038943998515605927,0.018313600029796363,0.01561600062996149,0.007127270260115769,0.0,0.0,0.0,0.0,0.0,0.08675199747085571,0.10662399977445602,0.09391999915242194,0.09391999915242194,0.006988099589086635,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.054687999188899994,0.021439999900758268,0.01539199985563755,0.012052764849597775,0.0,0.0,0.0,0.0,0.0,0.13488000631332397,0.1528639942407608,0.1431359991431236,0.1431359991431236,0.005436271464033599,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.041919998824596405,0.01899839974939823,0.015343999955803156,0.007989843526623287,0.0,0.0,0.0,0.0,0.0,0.06176000088453293,0.08374399691820145,0.06747519969940186,0.06747519969940186,0.0066067747128778,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016256000846624374,0.11353600025177002,0.042761600017547606,0.028960000723600388,0.029104301538020762,0.0,0.0,0.0,0.0,0.0,0.09734400361776352,0.14422400295734406,0.11392960175871848,0.11392960175871848,0.013198594600417867,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.034143999218940735,0.018918400071561335,0.01643200032413006,0.005500943993080684,0.0,0.0,0.0,0.0,0.0,0.12918399274349213,0.15087999403476715,0.13807999789714814,0.13807999789714814,0.007658330538677587,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016063999384641647,0.03641600161790848,0.0198208000510931,0.01780799962580204,0.0057264128169845765,0.0,0.0,0.0,0.0,0.0,0.22099199891090393,0.23904000222682953,0.2293503984808922,0.2293503984808922,0.004861342907006028,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.035840000957250595,0.018908800091594458,0.015792000107467175,0.0064374817924757475,0.0,0.0,0.0,0.0,0.0,0.10134399682283401,0.12201599776744843,0.10896319895982742,0.10896319895982742,0.006336330809165179,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.03417599946260452,0.017846399918198586,0.014800000004470348,0.006495007539635255,0.0,0.0,0.0,0.0,0.0,0.13126400113105774,0.15561600029468536,0.1389280006289482,0.1389280006289482,0.008381472811075022,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.03519999980926514,0.019168000388890504,0.01600000075995922,0.005995522477654695,0.0,0.0,0.0,0.0,0.0,0.21728000044822693,0.2343679964542389,0.2231455981731415,0.2231455981731415,0.004720730646739123,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.03670400008559227,0.018441599886864425,0.015023999847471714,0.006596535162793127,0.0,0.0,0.0,0.0,0.0,0.39321601390838623,0.4524799883365631,0.4058080047369003,0.4058080047369003,0.01578349755088941,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.022143999114632607,0.016912000067532063,0.015168000012636185,0.0028156089295136347,0.0,0.0,0.0,0.0,0.0,0.15587200224399567,0.3079040050506592,0.17838079929351805,0.17838079929351805,0.04355865575265927,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.02112000063061714,0.015516800060868263,0.01488000014796853,0.001940870731593904,0.0,0.0,0.0,0.0,0.0,0.21587200462818146,0.23561599850654602,0.22250880002975468,0.22250880002975468,0.006181951170646666,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.039264000952243805,0.023609600123018028,0.02131200022995472,0.007236979625711548,0.0,0.0,0.0,0.0,0.0,0.408735990524292,0.470335990190506,0.4336863994598388,0.4336863994598388,0.01844662383160074,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.025407999753952026,0.016227199975401164,0.014960000291466713,0.0031617375441736185,0.0,0.0,0.0,0.0,0.0,0.7412800192832947,0.7627840042114258,0.7464000046253203,0.7464000046253203,0.006112167448837547,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01462399959564209,0.02812799997627735,0.020652799773961304,0.021359999664127827,0.004308706957613102,0.028383498565450627,0.039859687970646644,0.032492258074592426,0.032492258074592426,0.00453597266208597,0.029312501176103633,0.04116431058787463,0.03355574193327539,0.03355574193327539,0.004684436757701648,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.034143999218940735,0.023171199765056372,0.024255999363958836,0.005908614918096971,0.03333159243114438,0.038935341782478095,0.03580428402241854,0.03580428402241854,0.002082270297044095,0.03633240903369937,0.04244065945634484,0.03902771507087562,0.03902771507087562,0.0022697354261490147,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.02611199952661991,0.019635199941694735,0.018112000077962875,0.0038298050749257795,0.04189529417991216,0.057484239920526384,0.04744885718421094,0.04744885718421094,0.004779830748455743,0.051672703037266184,0.07089975418195164,0.05852234134479412,0.05852234134479412,0.005895334539786378,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.029311999678611755,0.018662399891763926,0.01673599984496832,0.0044017112162725355,0.04322973959325901,0.05049827064705393,0.04535414343408448,0.04535414343408448,0.0022944156000240697,0.08733025617719538,0.10201372836398578,0.09162185574241775,0.09162185574241775,0.004635047631846023,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.026367999613285065,0.016336000058799982,0.01515199989080429,0.003415353455946402,0.06031842775160765,0.06618323188375198,0.06274415549817247,0.06274415549817247,0.001985647289644255,0.14768157653992678,0.16204076249052324,0.15362064543185072,0.15362064543185072,0.004861590945216247,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.02454400062561035,0.017167999967932702,0.016191999427974224,0.0028685016454498436,0.09128700688359712,0.09689150775996329,0.09360396051475776,0.09360396051475776,0.0013477542744916764,0.2740889887523892,0.2909164873209846,0.2810456356995366,0.2810456356995366,0.004046628526808561,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01881599985063076,0.03097599931061268,0.024598400108516216,0.024848000146448612,0.0037539437391565975,0.1035249255866932,0.10603132147437412,0.10399797220840973,0.10399797220840973,0.0007025109429056814,0.5652750707893444,0.5789606938874117,0.5678580377517648,0.5678580377517648,0.003835906384194897,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018624000251293182,0.043487999588251114,0.024460799992084503,0.019600000232458115,0.008922081629781394,0.196169204945307,0.2076140047945799,0.2008444429250931,0.2008444429250931,0.00394350953292805,1.1196708009293268,1.1849940417370974,1.1463555573610091,1.1463555573610091,0.022508285530529783,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.027135999873280525,0.03667199984192848,0.02945920005440712,0.028256000019609928,0.0029446678408169553,0.37757279619664613,0.3898113624476372,0.38075520430942184,0.38075520430942184,0.0036600203831042254,0.2522831942132049,0.2604606493092597,0.25440958703617433,0.25440958703617433,0.0024455194930253126,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.0435199998319149,0.049695998430252075,0.04502719938755036,0.04395199939608574,0.002035785660169308,1.1048984388245497,1.1189053886476108,1.1112371236754128,1.1112371236754128,0.0050220696724624985,0.1395495077239122,0.14131859607071193,0.14035008841031085,0.14035008841031085,0.0006342911944856293,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018783999606966972,0.024288000538945198,0.020627199858427047,0.019567999988794327,0.0019457052717059358,0.09455999732017517,0.12185599654912949,0.10207359939813614,0.10207359939813614,0.00753346544014261,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.027295999228954315,0.034752000123262405,0.02943360023200512,0.028528000228106976,0.0023159160681123767,0.14416000247001648,0.15904000401496887,0.14979200065135959,0.14979200065135959,0.00480624675866005,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.043455999344587326,0.05084799975156784,0.045500800386071204,0.04411200061440468,0.002490556062831049,0.24454399943351746,0.25865599513053894,0.2504959970712662,0.2504959970712662,0.003778494140301353,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07673600316047668,0.08374399691820145,0.07970559895038605,0.07873599976301193,0.0022907976135004057,0.445248007774353,0.4758400022983551,0.45409599840641024,0.45409599840641024,0.009133230340383306,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.043296001851558685,0.051072001457214355,0.044972800090909,0.04399999976158142,0.002451216824441962,0.6147199869155884,0.6290879845619202,0.6204927921295166,0.6204927921295166,0.004344846739788608,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07737600058317184,0.09123200178146362,0.08094720020890236,0.07980800047516823,0.004065264798368611,1.1744320392608643,1.1887680292129517,1.178323209285736,1.178323209285736,0.004395876469319665,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.03254399821162224,0.01810879958793521,0.01611199975013733,0.005058478889747962,0.0,0.0,0.0,0.0,0.0,0.06339199841022491,0.0841279998421669,0.07019519805908202,0.07019519805908202,0.006070126182471763,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.030271999537944794,0.018124799989163876,0.015711999498307705,0.004696400814632773,0.0,0.0,0.0,0.0,0.0,0.2739199995994568,0.2922239899635315,0.28281279802322384,0.28281279802322384,0.00633037978599564,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.022431999444961548,0.016844799742102623,0.015471999999135733,0.0027624803153841917,0.0,0.0,0.0,0.0,0.0,0.3909119963645935,0.4160960018634796,0.39996159672737125,0.39996159672737125,0.007037174636804898,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014240000396966934,0.035071998834609985,0.018764800019562246,0.015583999920636415,0.006305594700523817,0.0,0.0,0.0,0.0,0.0,0.7383679747581482,0.7597119808197021,0.7430047929286957,0.7430047929286957,0.006192645960911466,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.028991999104619026,0.019401599932461978,0.01665600063279271,0.005434953793780546,0.0,0.0,0.0,0.0,0.0,1.427008032798767,1.4517120122909546,1.4361984014511109,1.4361984014511109,0.008802755821028187,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.02844800055027008,0.01820160010829568,0.014944000169634819,0.004942002036909087,0.0,0.0,0.0,0.0,0.0,0.08361600339412689,0.11027199774980545,0.09058240056037903,0.09058240056037903,0.00872938604423622,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014112000353634357,0.023104000836610794,0.01648960020393133,0.015632000286132097,0.0027628828340349578,0.0,0.0,0.0,0.0,0.0,0.5063040256500244,0.5497599840164185,0.5168287932872773,0.5168287932872773,0.013557229606313293,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01616000011563301,0.029055999591946602,0.018780799955129622,0.017215999774634838,0.003794434947431941,0.0,0.0,0.0,0.0,0.0,0.7439360022544861,0.7719680070877075,0.7502080142498017,0.7502080142498017,0.00839205598262567,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015968000516295433,0.03046399913728237,0.018822400271892546,0.01726400014013052,0.004212536831927695,0.0,0.0,0.0,0.0,0.0,1.4256000518798828,1.449504017829895,1.4325888037681578,1.4325888037681578,0.0065448028108711165,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.027712000533938408,0.01633920017629862,0.014944000169634819,0.0038488220071983326,0.0,0.0,0.0,0.0,0.0,2.798719882965088,3.0184640884399414,2.8293471813201903,2.8293471813201903,0.06375662767704417,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.021407999098300934,0.01637439979240298,0.014992000069469213,0.0024463594774459265,0.0,0.0,0.0,0.0,0.0,0.09347199648618698,0.10473600029945374,0.09820479974150656,0.09820479974150656,0.004061668684999473,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.04790399968624115,0.020179199893027543,0.016447999514639378,0.009635010283506967,0.0,0.0,0.0,0.0,0.0,0.6221439838409424,0.6444799900054932,0.6277984082698822,0.6277984082698822,0.007234140179397069,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,8,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.03276799991726875,0.01921279989182949,0.015232000034302473,0.0065506148511265076,0.0,0.0,0.0,0.0,0.0,0.9111359715461731,0.9307839870452881,0.9151648044586183,0.9151648044586183,0.005528712062927265,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,16,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.02707199938595295,0.016512000095099212,0.014688000082969666,0.0038989080209321414,0.0,0.0,0.0,0.0,0.0,1.7645119428634644,1.7849279642105103,1.7684095859527589,1.7684095859527589,0.005876963340184193,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,32,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014240000396966934,0.029184000566601753,0.016825600154697896,0.014752000104635954,0.00457910514148248,0.0,0.0,0.0,0.0,0.0,3.4781761169433594,3.5388801097869873,3.490892815589905,3.490892815589905,0.01818910600692522,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,64,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014976000413298607,0.03139200061559677,0.01898880014196038,0.016848000697791576,0.005083715524393418,0.13752702814163098,0.14117629917511842,0.13848196486571557,0.13848196486571557,0.0009880564964713527,0.523336967410432,0.5372236808930884,0.5269708253945994,0.5269708253945994,0.00375988994658546,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,520,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,8,8,9,8,16384.0,0.1111111111111111,q512_8q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01833599992096424,0.02707199938595295,0.020995199866592883,0.01976000051945448,0.0028392656352050185,0.17817885890237703,0.18622915300900206,0.18109068484526028,0.18109068484526028,0.0027040006080457624,0.5449571488834201,0.5695788427872015,0.5538629212834322,0.5538629212834322,0.008270141985514729,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1040,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,16,16,17,16,16384.0,0.058823529411764705,q1k_16q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.02703999914228916,0.03308799862861633,0.028883199393749236,0.02759999968111515,0.002285758578932753,0.4688266550410815,0.48301665772804186,0.4727750380198454,0.4727750380198454,0.004396396389258256,1.0430453981052807,1.0746153117238624,1.051829759343436,1.051829759343436,0.009781101336187197,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,32,32,33,32,16384.0,0.030303030303030304,q2k_32q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.04368000105023384,0.059328000992536545,0.04809600040316582,0.04617599956691265,0.005158792915002645,1.3509461459747514,1.3759066409666496,1.3589365122072,1.3589365122072,0.008008877716183384,0.9213738861449998,0.9383974724214122,0.9268234851606594,0.9268234851606594,0.005462224239661061,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,16,16,17,16,32768.0,0.058823529411764705,q4k_16q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.026944000273942947,0.040511999279260635,0.030291200056672095,0.02817599941045046,0.004386386489305873,0.5071830964059985,0.5142792136001758,0.5096392092471257,0.5096392092471257,0.0022059272685869546,2.175632932188972,2.2060727208328075,2.186168772243963,2.186168772243963,0.009462633998570079,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,32,32,33,32,32768.0,0.030303030303030304,q2k_32q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018303999677300453,0.03017600066959858,0.02039040010422468,0.018943999893963337,0.0034612051983613614,0.21341429693945616,0.21552776300295579,0.21393496609766816,0.21393496609766816,0.0005736773262009222,4.617401495144284,4.663128147488988,4.628666619290515,4.628666619290515,0.012412001359412127,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,64,64,65,64,32768.0,0.015384615384615385,q1k_64q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.02364799939095974,0.01809599995613098,0.016352000646293163,0.0035481127058959038,0.04822399839758873,0.08566399663686752,0.05961279980838299,0.05961279980838299,0.011445665413968877,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.020864000543951988,0.01668160008266568,0.015664000064134598,0.0025769063833097584,0.049695998430252075,0.08057600259780884,0.05882879942655563,0.05882879942655563,0.009515126108519331,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.028704000636935234,0.017430400010198355,0.015056000091135502,0.004349294613335555,0.049855999648571014,0.07366400212049484,0.05459520071744919,0.05459520071744919,0.0069610920757925574,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.03161599859595299,0.017788799852132796,0.015711999963968992,0.005005385723318659,0.06102399900555611,0.08179199695587158,0.06650560013949873,0.06650560013949873,0.006947995595801105,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.04416000097990036,0.019200000166893005,0.015488000120967627,0.008561241323364038,0.08054400235414505,0.09196799993515015,0.08607039973139763,0.08607039973139763,0.004145329035483754,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017855999991297722,0.023391999304294586,0.019667199812829494,0.018463999964296818,0.0022577669687832585,0.18729600310325623,0.20585599541664124,0.19546559900045393,0.19546559900045393,0.006339068824303663,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.026240000501275063,0.03446400165557861,0.028297600522637367,0.027088000439107418,0.0025148441522922374,0.5754240155220032,0.5889919996261597,0.5800191938877105,0.5800191938877105,0.003858869273829596,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04182400181889534,0.047200001776218414,0.043036799877882004,0.0423360001295805,0.0017073405772076728,2.063199996948242,2.0787200927734375,2.067151999473572,2.067151999473572,0.004959651271127835,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.05648000165820122,0.02270399993285537,0.017935999669134617,0.012377915150727689,0.049536000937223434,0.07196799665689468,0.056015999615192415,0.056015999615192415,0.0070476637552742884,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01408000010997057,0.021344000473618507,0.01611520005390048,0.014928000047802925,0.0025499884993961702,0.07072000205516815,0.2642880082130432,0.1588256008923054,0.1588256008923054,0.053220347086102376,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01360000018030405,0.03014400042593479,0.016975999902933837,0.015056000091135502,0.004715159697364111,0.08393599838018417,0.11036799848079681,0.09160000011324881,0.09160000011324881,0.007911669434472792,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.020767999812960625,0.016233599931001663,0.015392000321298838,0.002202615907995427,0.1998399943113327,0.22070400416851044,0.20855360180139543,0.20855360180139543,0.00689307200230667,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.033440001308918,0.018684800155460833,0.016048000194132328,0.00553991005639174,0.6043199896812439,0.635807991027832,0.6126143991947173,0.6126143991947173,0.008745933953408096,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013824000023305416,0.03359999880194664,0.017811199743300678,0.014944000169634819,0.005926140483565472,0.0,0.0,0.0,0.0,0.0,0.045471999794244766,0.07539200037717819,0.054758400097489356,0.054758400097489356,0.010253548506101549,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.02409599907696247,0.01641279999166727,0.01473599998280406,0.003347158638713987,0.0,0.0,0.0,0.0,0.0,0.0461760014295578,0.07529599964618683,0.05460800044238568,0.05460800044238568,0.009748937798340135,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.028416000306606293,0.018611199874430894,0.01598400017246604,0.005209875093863647,0.0,0.0,0.0,0.0,0.0,0.048128001391887665,0.07897599786520004,0.061353600397706036,0.061353600397706036,0.010488153655157845,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014112000353634357,0.025728000327944756,0.016092800162732603,0.01512000011280179,0.003300888123052605,0.0,0.0,0.0,0.0,0.0,0.04864000156521797,0.07648000121116638,0.05810560062527656,0.05810560062527656,0.009473544218404408,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.03551999852061272,0.018588799890130757,0.016064000315964222,0.006071057437992447,0.0,0.0,0.0,0.0,0.0,0.04822399839758873,0.07862400263547897,0.05660480037331582,0.05660480037331582,0.009565394213730401,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.028831999748945236,0.01699519995599985,0.015024000313133001,0.004285000744868188,0.0,0.0,0.0,0.0,0.0,0.04854400083422661,0.06719999760389328,0.05778240002691746,0.05778240002691746,0.006852125554679805,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0144640002399683,0.024927999824285507,0.0161183999851346,0.01521599991247058,0.0029774808524673907,0.0,0.0,0.0,0.0,0.0,0.05379199981689453,0.08966399729251862,0.06270079985260964,0.06270079985260964,0.009983591277092696,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.03001599945127964,0.017648000083863736,0.01547200046479702,0.004585126309484848,0.0,0.0,0.0,0.0,0.0,0.061664000153541565,0.07692799717187881,0.06704320013523103,0.06704320013523103,0.005500191798490629,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.026367999613285065,0.016947199776768684,0.015039999969303608,0.0037951566103550205,0.0,0.0,0.0,0.0,0.0,0.08799999952316284,0.111455999314785,0.0964031994342804,0.0964031994342804,0.007397541615558088,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01369599997997284,0.021247999742627144,0.015359999984502793,0.014640000183135271,0.0020942770950814317,0.0,0.0,0.0,0.0,0.0,0.051711998879909515,0.07065600156784058,0.058054400235414506,0.058054400235414506,0.006633034815910025,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014208000153303146,0.0307839997112751,0.017148799914866685,0.015039999969303608,0.004882374686312284,0.0,0.0,0.0,0.0,0.0,0.061919998377561576,0.07843200117349625,0.06628479920327664,0.06628479920327664,0.004962852689801192,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013887999579310417,0.02969600073993206,0.017500799987465142,0.015232000034302473,0.00467273319705314,0.0,0.0,0.0,0.0,0.0,0.08819200098514557,0.11097600311040878,0.09493440166115762,0.09493440166115762,0.007509235042985577,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.022112000733613968,0.01751680001616478,0.016047999262809753,0.0030306621792915785,0.0,0.0,0.0,0.0,0.0,0.13065600395202637,0.15110400319099426,0.13857279866933822,0.13857279866933822,0.00750137841249771,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.04012800008058548,0.01892479993402958,0.01550400024279952,0.007459545267816961,0.0,0.0,0.0,0.0,0.0,0.06278400123119354,0.08259200304746628,0.0704512007534504,0.0704512007534504,0.005979055984382744,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.02236800082027912,0.016332800220698118,0.014928000047802925,0.002784044363186731,0.0,0.0,0.0,0.0,0.0,0.1003199964761734,0.1279360055923462,0.10921279862523078,0.10921279862523078,0.00862769617046716,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.0225600004196167,0.016128000058233737,0.014800000004470348,0.002958953332547708,0.0,0.0,0.0,0.0,0.0,0.13116799294948578,0.14812800288200378,0.13783999979496003,0.13783999979496003,0.005696384361148053,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014208000153303146,0.029983999207615852,0.017468800116330386,0.01508800033479929,0.0047379550962483065,0.0,0.0,0.0,0.0,0.0,0.217631995677948,0.2447360008955002,0.22715839892625808,0.22715839892625808,0.008831828221847138,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014047999866306782,0.02304000034928322,0.016512000095099212,0.014512000139802694,0.0035026774828624254,0.0,0.0,0.0,0.0,0.0,0.11020799726247787,0.12307199835777283,0.11600959971547126,0.11600959971547126,0.004667637266950902,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014112000353634357,0.042080000042915344,0.017510399967432023,0.014607999939471483,0.00823117883530167,0.0,0.0,0.0,0.0,0.0,0.15702399611473083,0.17587199807167053,0.16399359852075576,0.16399359852075576,0.006588299074676393,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013919999822974205,0.0208320003002882,0.015299199987202883,0.01462399959564209,0.001916768086505386,0.0,0.0,0.0,0.0,0.0,0.21779200434684753,0.2415360063314438,0.2260768011212349,0.2260768011212349,0.007251352080685236,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014015999622642994,0.021088000386953354,0.015619200188666582,0.01473599998280406,0.002013227452302141,0.0,0.0,0.0,0.0,0.0,0.3959999978542328,0.4152640104293823,0.40332479774951924,0.40332479774951924,0.006942401431914052,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014175999909639359,0.03379200026392937,0.020595200080424547,0.019600000232458115,0.006548754248881344,0.026192623739694512,0.040006882507168426,0.029155180178492036,0.029155180178492036,0.00408828748438241,0.024591375524545756,0.037561119537986146,0.027372820355088746,0.027372820355088746,0.0038383559348575944,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.020896000787615776,0.015318400040268899,0.014431999996304512,0.0019640312960926966,0.029349018208693862,0.06236262941356679,0.03714313592014963,0.03714313592014963,0.009618313791872569,0.028826981462526914,0.06125337308649041,0.036482463672774496,0.036482463672774496,0.009447230957011863,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.032127998769283295,0.017286399938166143,0.014479999896138906,0.005536495446636193,0.03273085874558354,0.04394578491937082,0.03563837490653034,0.03563837490653034,0.003429601730256567,0.03488514202593899,0.04683821345079978,0.037984025407085474,0.037984025407085474,0.0036553316361902684,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.013856000266969204,0.021503999829292297,0.015078400075435639,0.01425600005313754,0.002238435975478849,0.042100813549974185,0.051784144690147756,0.045378692890289625,0.045378692890289625,0.003184109940650555,0.05111518843748309,0.06287185663927425,0.05509490773570219,0.05509490773570219,0.0038658725544299132,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.02687999978661537,0.017667199857532977,0.01566399959847331,0.003864811846387173,0.048475323773821306,0.05599956978723733,0.05123499252968345,0.05123499252968345,0.002427379820423941,0.08429268135885387,0.09737642835214408,0.0890914090616175,0.0890914090616175,0.0042209177332077005,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01462399959564209,0.03359999880194664,0.019804799742996693,0.016032000072300434,0.006750519908145474,0.07121508474579985,0.07292308367136396,0.07194410845270183,0.07194410845270183,0.0005500065915943844,0.14760091249712767,0.15114092373010238,0.14911189243564577,0.14911189243564577,0.0011399477384397005,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.021856000646948814,0.016835200227797033,0.015263999812304974,0.00283854448975065,0.08146338272142935,0.08560865714384096,0.0834932625520734,0.0834932625520734,0.0012259635905347874,0.2782486219401307,0.29240733788179385,0.2851819365989658,0.2851819365989658,0.004187435731481665,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.04495999962091446,0.02143679987639189,0.015856000129133463,0.009709987872683342,0.1194459208702178,0.12302524755181463,0.12053885718696096,0.12053885718696096,0.001005118119341339,0.5597220650459199,0.5764947443228802,0.5648435507167102,0.5648435507167102,0.004709970715400788,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018112000077962875,0.026496000587940216,0.019318400137126445,0.018432000651955605,0.0024249605112359905,0.19770253574610402,0.222811797868348,0.2054811520619412,0.2054811520619412,0.008000944254868043,0.13941746080159492,0.157124211777114,0.14490284788179197,0.14490284788179197,0.005642170080515992,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.02595200017094612,0.03155200183391571,0.02727359998971224,0.026575999334454536,0.0016260948764843166,0.6014684881116659,0.6095472988212,0.6046757700946376,0.6046757700946376,0.0023537435563177303,0.11325152264578045,0.11477269562841545,0.11385542721485654,0.11385542721485654,0.0004431903698023628,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.03359999880194664,0.01814719969406724,0.015375999733805656,0.005678506740662529,0.06774400174617767,0.07891199737787247,0.07312640026211739,0.07312640026211739,0.003826583051422731,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01788800023496151,0.028543999418616295,0.021340799890458582,0.019504000432789326,0.003718627037219618,0.09548799693584442,0.1327359974384308,0.10823359936475753,0.10823359936475753,0.013230635292043864,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02627200074493885,0.030368000268936157,0.027184000052511693,0.02643200010061264,0.0013545679205210022,0.14364799857139587,0.1597760021686554,0.15008639842271806,0.15008639842271806,0.005367723415171222,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04150399938225746,0.04726399853825569,0.042950399965047834,0.04224000126123428,0.001720147501765378,0.2433920055627823,0.28963199257850647,0.2549152016639709,0.2549152016639709,0.013450991019687407,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.025887999683618546,0.03407999873161316,0.028303999826312064,0.026367999613285065,0.0028877495368841042,0.325439989566803,0.3441599905490875,0.33442879617214205,0.33442879617214205,0.005693597811441922,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04137599840760231,0.05084799975156784,0.044828799366950986,0.043087998405098915,0.003560363865797613,0.6110399961471558,0.6421759724617004,0.6204223990440368,0.6204223990440368,0.011214490370794758,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014816000126302242,0.02364799939095974,0.016668799985200166,0.01592000015079975,0.0025515238179941247,0.0,0.0,0.0,0.0,0.0,0.0544000007212162,0.09014400094747543,0.06511679962277411,0.06511679962277411,0.013005726711295521,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.0208320003002882,0.016604799963533878,0.01566399959847331,0.0021353594266203244,0.0,0.0,0.0,0.0,0.0,0.17871999740600586,0.1961279958486557,0.18568639904260634,0.18568639904260634,0.004566142885274747,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014431999996304512,0.02006400004029274,0.015619200002402068,0.01508800033479929,0.001572984783715635,0.0,0.0,0.0,0.0,0.0,0.2730880081653595,0.29721599817276,0.2815328001976013,0.2815328001976013,0.007016534727616923,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.02755199931561947,0.018678399827331306,0.015919999685138464,0.004323555372382858,0.0,0.0,0.0,0.0,0.0,0.3893119990825653,0.44041600823402405,0.40225600004196166,0.40225600004196166,0.013442998165884852,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014303999952971935,0.02659199945628643,0.016748800035566093,0.015343999955803156,0.0036412341868394082,0.0,0.0,0.0,0.0,0.0,0.7404800057411194,0.9689919948577881,0.8451807916164398,0.8451807916164398,0.08637455920036795,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.02160000056028366,0.016752000153064727,0.01521599991247058,0.0025167650350367246,0.0,0.0,0.0,0.0,0.0,0.06412799656391144,0.08956799656152725,0.07242240011692047,0.07242240011692047,0.009797120588901621,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.022911999374628067,0.016137600038200618,0.015343999955803156,0.002330911555470513,0.0,0.0,0.0,0.0,0.0,0.3128319978713989,0.3282879889011383,0.3203647971153259,0.3203647971153259,0.004598568238907996,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.03574400022625923,0.01919359974563122,0.01583999954164028,0.006642521913489215,0.0,0.0,0.0,0.0,0.0,0.5050879716873169,0.5311999917030334,0.511932796239853,0.511932796239853,0.007150929647317677,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.02595200017094612,0.016992000117897987,0.015456000342965126,0.003390731937723684,0.0,0.0,0.0,0.0,0.0,0.7385600209236145,0.7681919932365417,0.7483008027076722,0.7483008027076722,0.010214373356208012,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.038975998759269714,0.01952639976516366,0.015327999833971262,0.007695927285621061,0.0,0.0,0.0,0.0,0.0,1.4228800535202026,1.5237760543823242,1.4435008168220522,1.4435008168220522,0.0342955291725742,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.03907199949026108,0.01793599994853139,0.015248000156134367,0.007167103363234667,0.0,0.0,0.0,0.0,0.0,0.06947200000286102,0.08857599645853043,0.07469440028071403,0.07469440028071403,0.00583249952929747,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.02175999991595745,0.016710399929434062,0.015327999833971262,0.002705383977079183,0.0,0.0,0.0,0.0,0.0,0.388480007648468,0.4073280096054077,0.3966591984033584,0.3966591984033584,0.004487315516095964,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,8,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0144640002399683,0.022048000246286392,0.017011200170964004,0.015392000321298838,0.002776899649845722,0.0,0.0,0.0,0.0,0.0,0.622048020362854,0.6347839832305908,0.6262047946453094,0.6262047946453094,0.004593360122958751,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,16,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.02937600016593933,0.01847040019929409,0.015344000421464443,0.005043809142122341,0.0,0.0,0.0,0.0,0.0,0.9105280041694641,0.9304640293121338,0.914108806848526,0.914108806848526,0.00563919268816644,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,32,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01462399959564209,0.039903998374938965,0.01791359977796674,0.015440000221133232,0.007367547649297217,0.0,0.0,0.0,0.0,0.0,1.764799952507019,1.7965760231018066,1.770739197731018,1.770739197731018,0.009082122770320404,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,64,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015168000012636185,0.03187200054526329,0.018553599901497363,0.016127999871969223,0.0050628774268006264,0.16963527081512533,0.1737871320906266,0.17088926838108623,0.17088926838108623,0.0011703114258121128,0.47362872483230506,0.48522089403242025,0.47712993814280913,0.47712993814280913,0.0032675581298664976,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,520,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,8,8,9,8,16384.0,0.1111111111111111,q512_8q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.03868800029158592,0.01921919994056225,0.016959999687969685,0.006691309533030663,0.1589600576212269,0.16117782913137854,0.15969057520605917,0.15969057520605917,0.0006212984448748182,0.5199519263456005,0.5272061673552852,0.5223414198520004,0.5223414198520004,0.002032242112153396,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1040,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,16,16,17,16,16384.0,0.058823529411764705,q1k_16q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018400000408291817,0.024320000782608986,0.019910399988293647,0.0191040001809597,0.001841532763984352,0.25650752966102763,0.27066608538463055,0.259736894547936,0.259736894547936,0.00462927315947332,0.5278764825612624,0.5570139063374764,0.5345223138928448,0.5345223138928448,0.009526755161797178,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,32,32,33,32,16384.0,0.030303030303030304,q2k_32q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.026048000901937485,0.03728000074625015,0.028636799938976765,0.02705600019544363,0.003313953649011259,0.9270006318443208,0.9712965120641314,0.93480767601568,0.93480767601568,0.012612551450284608,0.8181833128578277,0.8572794566782395,0.8250739157811953,0.8250739157811953,0.01113200873299586,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,16,16,17,16,32768.0,0.058823529411764705,q4k_16q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.018079999834299088,0.037696000188589096,0.022092800214886667,0.019024000503122807,0.005986278786633071,0.2839857165542317,0.2876110048757805,0.2849506939696605,0.2849506939696605,0.0009995178425916847,1.0871823008331585,1.101060989333509,1.0908765231323903,1.0908765231323903,0.0038264533900426207,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,32,32,33,32,32768.0,0.030303030303030304,q2k_32q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.015072000212967396,0.025567999109625816,0.01726400014013052,0.015728000551462173,0.0031324465940990903,0.137270464802061,0.13799613818579368,0.13751499486424038,0.13751499486424038,0.00025221761530472904,2.3021855212208884,2.314355908780759,2.3062865750744197,2.3062865750744197,0.004229983070201486,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,64,64,65,64,32768.0,0.015384615384615385,q1k_64q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014560000039637089,0.022784000262618065,0.016435200069099664,0.015519999898970127,0.0023688301421469523,0.04879999905824661,0.09139200299978256,0.06054079942405224,0.06054079942405224,0.012152608702448775,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,64,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,False,0.0,64.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014816000126302242,0.02844800055027008,0.017008000146597625,0.015696000307798386,0.003941466294662679,0.047807998955249786,0.07356800138950348,0.05626560002565384,0.05626560002565384,0.00842179125412236,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,128,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,False,0.0,128.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.053408000618219376,0.019353600218892097,0.01532800029963255,0.01138302400841626,0.048448000103235245,0.0785600021481514,0.0556256003677845,0.0556256003677845,0.009348274502616908,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,256,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,False,0.0,256.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015039999969303608,0.03139200061559677,0.01823679991066456,0.016159999649971724,0.004860071238302512,0.055424001067876816,0.08505599945783615,0.0640383992344141,0.0640383992344141,0.00921448636178623,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,512,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,False,0.0,512.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.026528000831604004,0.017324799951165915,0.01536000007763505,0.0036004822686428305,0.07660800218582153,0.0942080020904541,0.08209280073642732,0.08209280073642732,0.00515895587669752,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.021247999742627144,0.016403199825435876,0.01532800029963255,0.001995897022647934,0.11395200341939926,0.15113599598407745,0.12431039959192276,0.12431039959192276,0.011164431123683732,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017184000462293625,0.028672000393271446,0.019865600019693376,0.017823999747633934,0.0035798491315929977,0.3171840012073517,0.3341119885444641,0.3261695951223373,0.3261695951223373,0.005111046452878918,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024639999493956566,0.030400000512599945,0.02656640000641346,0.02556800004094839,0.0020189846603237303,1.0648640394210815,1.0828479528427124,1.0715327858924866,1.0715327858924866,0.005558639263049851,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014976000413298607,0.021695999428629875,0.017305599898099898,0.01593599934130907,0.0025718046517268054,0.04956800118088722,0.07932800054550171,0.06228480041027069,0.06228480041027069,0.01027160349757827,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,64,448.0,True,FLASH_ATTN,False,vllm020_batch_spec,[64],64,64,64,64.0,True,0.0,0.0,0.0,True,448.0,512.0,64,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q64s512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01539199985563755,0.03580800071358681,0.019686400331556796,0.017136000096797943,0.005918387811304003,0.05158400163054466,0.10713600367307663,0.06364160068333148,0.06364160068333148,0.015832957809696766,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,128,896.0,True,FLASH_ATTN,False,vllm020_batch_spec,[128],128,128,128,128.0,True,0.0,0.0,0.0,True,896.0,1024.0,128,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q128s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015168000012636185,0.02223999984562397,0.016672000009566545,0.015887999907135963,0.0020934945946034563,0.06521599739789963,0.08902399986982346,0.07520959973335266,0.07520959973335266,0.007913840684102929,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,256,1792.0,True,FLASH_ATTN,False,vllm020_batch_spec,[256],256,256,256,256.0,True,0.0,0.0,0.0,True,1792.0,2048.0,256,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q256s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015231999568641186,0.04028800129890442,0.019971200078725816,0.01646399963647127,0.007351305886577286,0.14467200636863708,0.16844800114631653,0.15363519936800005,0.15363519936800005,0.008174435899956223,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,512,3584.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,3584.0,4096.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015519999898970127,0.02304000034928322,0.01775679988786578,0.016784000210464,0.0025077243712082584,0.33740800619125366,0.35343998670578003,0.3445120006799698,0.3445120006799698,0.00445648463590358,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,1024,7168.0,True,FLASH_ATTN,False,vllm020_batch_spec,[1024],1024,1024,1024,1024.0,True,0.0,0.0,0.0,True,7168.0,8192.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1ks8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015647999942302704,0.02393599972128868,0.01809599995613098,0.01654400024563074,0.002998393102466254,0.0,0.0,0.0,0.0,0.0,0.0504320003092289,0.0843840017914772,0.060083200410008426,0.060083200410008426,0.00986959318572296,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01603199914097786,0.030047999694943428,0.019510399922728537,0.017680000513792038,0.004065185265963332,0.0,0.0,0.0,0.0,0.0,0.05004800111055374,0.07036799937486649,0.059315200522542,0.059315200522542,0.006537768821329647,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.02393599972128868,0.018035199772566558,0.016512000001966953,0.0030667689116777724,0.0,0.0,0.0,0.0,0.0,0.05100800096988678,0.06735999882221222,0.058387200161814694,0.058387200161814694,0.005832787739241381,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.026208000257611275,0.017500799987465142,0.01646399963647127,0.0030666103306165714,0.0,0.0,0.0,0.0,0.0,0.05023999884724617,0.07254400104284286,0.057254400476813315,0.057254400476813315,0.006890853653068151,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.027327999472618103,0.0179776000790298,0.01648000068962574,0.003783417447531392,0.0,0.0,0.0,0.0,0.0,0.04819199815392494,0.07100799679756165,0.05621119923889638,0.05621119923889638,0.007824391484124725,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,128.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s128,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015647999942302704,0.036448001861572266,0.019136000238358975,0.016704000532627106,0.006076530095624803,0.0,0.0,0.0,0.0,0.0,0.047488000243902206,0.08441600203514099,0.0588383998721838,0.0588383998721838,0.011275940726332522,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015135999768972397,0.033952001482248306,0.02119360016658902,0.018000000156462193,0.007136646614305304,0.0,0.0,0.0,0.0,0.0,0.04931199923157692,0.06992000341415405,0.05755840018391609,0.05755840018391609,0.007297587694315226,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.034272000193595886,0.0204415999352932,0.017311999574303627,0.00695404701803013,0.0,0.0,0.0,0.0,0.0,0.05215999856591225,0.0735040009021759,0.06117440015077591,0.06117440015077591,0.007381118436894922,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.03743999823927879,0.02012479966506362,0.01775999926030636,0.006181045509079057,0.0,0.0,0.0,0.0,0.0,0.06355199962854385,0.08508799970149994,0.07019200026988984,0.07019200026988984,0.0062246580442117845,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,1024.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s1k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015552000142633915,0.032607998698949814,0.01959999995306134,0.017487999983131886,0.004882475068460749,0.0,0.0,0.0,0.0,0.0,0.04918399825692177,0.0865280032157898,0.05973760038614274,0.05973760038614274,0.011546847942113974,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015168000012636185,0.02675200067460537,0.017430400010198355,0.016560000367462635,0.003243135094239819,0.0,0.0,0.0,0.0,0.0,0.052671998739242554,0.08367999643087387,0.06238719932734965,0.06238719932734965,0.011207824780630104,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.03612799942493439,0.019327999837696553,0.01688000001013279,0.006058251425153085,0.0,0.0,0.0,0.0,0.0,0.06364800035953522,0.07878399640321732,0.06935679838061332,0.06935679838061332,0.004515588328677643,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.03711999952793121,0.019670399930328132,0.017152000218629837,0.006165994646522264,0.0,0.0,0.0,0.0,0.0,0.09071999788284302,0.11507199704647064,0.10252480059862136,0.10252480059862136,0.008782544051535657,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,2048.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015039999969303608,0.026528000831604004,0.018396800104528665,0.01601599995046854,0.004279788048986283,0.0,0.0,0.0,0.0,0.0,0.05331199988722801,0.07977599650621414,0.06076480001211167,0.06076480001211167,0.008761579122069606,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.02643200010061264,0.01726400004699826,0.015855999663472176,0.003210008417242029,0.0,0.0,0.0,0.0,0.0,0.062431998550891876,0.08246400207281113,0.06970879957079888,0.06970879957079888,0.007016341676068233,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014911999925971031,0.02223999984562397,0.0166015999391675,0.015887999907135963,0.00204913969129354,0.0,0.0,0.0,0.0,0.0,0.10127999633550644,0.1141119971871376,0.10621120035648347,0.10621120035648347,0.004029318311754605,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.03363199904561043,0.019305599946528675,0.016671999357640743,0.0055445582307981234,0.0,0.0,0.0,0.0,0.0,0.1319040060043335,0.15839999914169312,0.14040640145540234,0.14040640145540234,0.007998041073596942,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,4096.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s4k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014368000440299511,0.04447999969124794,0.018908800091594458,0.0157279996201396,0.0086814937461721,0.0,0.0,0.0,0.0,0.0,0.06428799778223038,0.08982399851083755,0.07349760085344315,0.07349760085344315,0.008605284512197258,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.028672000393271446,0.01890560006722808,0.016080000437796116,0.004797584627815021,0.0,0.0,0.0,0.0,0.0,0.11123199760913849,0.14115199446678162,0.11942399889230729,0.11942399889230729,0.008513394706791027,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014271999709308147,0.024927999824285507,0.016915200091898442,0.015216000378131866,0.003374147499442635,0.0,0.0,0.0,0.0,0.0,0.15887999534606934,0.18111999332904816,0.16934399753808976,0.16934399753808976,0.007415181260761123,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014336000196635723,0.026944000273942947,0.017737600207328796,0.015199999790638685,0.00415598714375255,0.0,0.0,0.0,0.0,0.0,0.2192319929599762,0.23472000658512115,0.22809920012950893,0.22809920012950893,0.004730841376327335,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,8192.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s8k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.05052800104022026,0.020320000313222408,0.015520000364631414,0.010604522177924678,0.024270629882498958,0.03340247625954076,0.028446344104128624,0.028446344104128624,0.0032330369099793834,0.023697370291069768,0.03261352722995356,0.027774456325453972,0.027774456325453972,0.0031566742680923386,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,72,,,,,,,,False,,,64,BF16,generic,none,CUDA_EVENT,True,[64],[0],"[512, 512, 512, 512, 512, 512, 512, 512]",1,8,8,9,8,512.0,0.1111111111111111,q64_8q1s512,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.015359999611973763,0.033663999289274216,0.019987199828028678,0.018240000121295452,0.005522929139253732,0.0259194055660947,0.03719755183990719,0.029916029687899703,0.029916029687899703,0.003966666590554318,0.027104595853449518,0.03889844644729374,0.03128396954022015,0.03128396954022015,0.004148046317967881,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,136,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,8,8,9,8,1024.0,0.1111111111111111,q128_8q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.03299200162291527,0.019840000104159115,0.016207999549806118,0.006546343008726814,0.02587869595769926,0.03763167265431482,0.030174939058162802,0.030174939058162802,0.0037303581782277364,0.026473304070195713,0.03849632587654989,0.03086826083864964,0.03086826083864964,0.003816069654529222,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,144,,,,,,,,False,,,128,BF16,generic,none,CUDA_EVENT,True,[128],[0],"[1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024]",1,16,16,17,16,1024.0,0.058823529411764705,q128_16q1s1k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.013824000023305416,0.021023999899625778,0.016304000187665223,0.015584000386297703,0.0023236165806545476,0.031810621525966996,0.04156949936878106,0.0346749350032807,0.0346749350032807,0.003130209181143985,0.035677378270900374,0.04662250161636451,0.038889864871740294,0.038889864871740294,0.0035107033960828727,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,272,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,16,16,17,16,2048.0,0.058823529411764705,q256_16q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.02175999991595745,0.01569600012153387,0.015008000191301107,0.0020882666168036863,0.038211712107062853,0.07212229256520057,0.04364509673334097,0.04364509673334097,0.009671953074025085,0.0476442859917874,0.08992570455184198,0.05441890342616107,0.05441890342616107,0.01205947791784038,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,288,,,,,,,,False,,,256,BF16,generic,none,CUDA_EVENT,True,[256],[0],"[2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048]",1,32,32,33,32,2048.0,0.030303030303030304,q256_32q1s2k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014368000440299511,0.033824000507593155,0.017628800217062236,0.014864000026136637,0.005791495403857738,0.05214261250030033,0.06266261508706669,0.05677791295527661,0.05677791295527661,0.0030298223079651514,0.08648138506878382,0.10392938682791132,0.09416928531647478,0.09416928531647478,0.005025126612204489,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,544,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q512_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.031199999153614044,0.017900799959897996,0.015343999955803156,0.004974475661316249,0.06411958891421111,0.07405276123263956,0.06793047918211377,0.06793047918211377,0.0033918658556700006,0.14058441263169497,0.16236323591492058,0.1489399211274489,0.1489399211274489,0.00743678300375353,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,576,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,64,64,65,64,4096.0,0.015384615384615385,q512_64q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.03855999931693077,0.018495999928563833,0.015647999942302704,0.006918530056761627,0.09872985549401277,0.10683454583043753,0.10185316839884552,0.10185316839884552,0.0020802254037042074,0.2743261390166379,0.2968454508984596,0.2830044295482752,0.2830044295482752,0.005780016596065092,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192]",1,64,64,65,64,8192.0,0.015384615384615385,q1k_64q1s8k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014911999925971031,0.030400000512599945,0.01977920001372695,0.01726400014013052,0.005350883464206169,0.13918872472233365,0.16279522855335207,0.1501912864839173,0.1501912864839173,0.008992185529011513,0.11892328861766266,0.13909276049083735,0.1283239123428725,0.1283239123428725,0.007682951884956939,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,32,32,33,32,4096.0,0.030303030303030304,q2k_32q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01727999933063984,0.02223999984562397,0.01819519978016615,0.017680000513792038,0.0014397298270620873,0.3728044181625443,0.38295504353701676,0.3761264483787333,0.3761264483787333,0.0033660272332490977,0.07967557017401883,0.08184495665371805,0.08038555277807365,0.08038555277807365,0.0007193856241088455,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096]",1,16,16,17,16,4096.0,0.058823529411764705,q4k_16q1s4k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.034591998904943466,0.01941439984366298,0.01756799966096878,0.005541380584373771,0.05951999872922897,0.08268799632787704,0.06715519949793816,0.06715519949793816,0.006657802116288364,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,2,1024,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512]",1024,512,512,512.0,True,0.0,0.0,0.0,False,0.0,1024.0,1024,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.03283200040459633,0.019180799927562477,0.016543999314308167,0.0052187911233635975,0.07199999690055847,0.08675199747085571,0.07749439924955369,0.07749439924955369,0.004849874741156772,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,4,2048,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512]",2048,512,512,512.0,True,0.0,0.0,0.0,False,0.0,2048.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01724799908697605,0.02284800074994564,0.01928640007972717,0.018400000408291817,0.0020641390157565697,0.09676799923181534,0.12310399860143663,0.10618879944086074,0.10618879944086074,0.008982738207839057,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512]",4096,512,512,512.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024224000051617622,0.03315199911594391,0.027436799928545953,0.027328000403940678,0.002679154874546328,0.14716799557209015,0.16412800550460815,0.15470399856567385,0.15470399856567385,0.005423454433987419,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512]",8192,512,512,512.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q512,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01833599992096424,0.04806400090456009,0.026252799853682517,0.022672000341117382,0.00878438440429033,0.1844799965620041,0.2072959989309311,0.19359359890222552,0.19359359890222552,0.007663539820967659,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,2,4096,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048]",4096,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,4096.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,2q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024480000138282776,0.04979199916124344,0.029081599973142146,0.025679999962449074,0.007227422044689197,0.34147199988365173,0.37968000769615173,0.3583200007677078,0.3583200007677078,0.011804422100726231,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,4,8192,0.0,True,FLASH_ATTN,False,vllm020_batch_spec,"[2048, 2048, 2048, 2048]",8192,2048,2048,2048.0,True,0.0,0.0,0.0,False,0.0,8192.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,4q2k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014720000326633453,0.023744000121951103,0.017753600236028434,0.016368000768125057,0.003061040281616705,0.0,0.0,0.0,0.0,0.0,0.05686400085687637,0.1090880036354065,0.06629760004580021,0.06629760004580021,0.014803727026812366,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.021088000386953354,0.01647359998896718,0.015840000472962856,0.0017964402433206,0.0,0.0,0.0,0.0,0.0,0.08540800213813782,0.09961599856615067,0.09146559983491898,0.09146559983491898,0.00447423706371901,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014560000039637089,0.04156799986958504,0.018512000143527985,0.015584000386297703,0.007849701681877904,0.0,0.0,0.0,0.0,0.0,0.17948800325393677,0.194815993309021,0.1866239994764328,0.1866239994764328,0.004156328241374654,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.029632000252604485,0.019449600111693145,0.016736000776290894,0.005126811425136928,0.0,0.0,0.0,0.0,0.0,0.27529600262641907,0.2898879945278168,0.2825664013624191,0.2825664013624191,0.004542801609674093,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014399999752640724,0.031328000128269196,0.019759999960660933,0.016367999836802483,0.006266303740589241,0.0,0.0,0.0,0.0,0.0,0.39190399646759033,0.4079039990901947,0.3987520009279252,0.3987520009279252,0.0037367727509362725,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,16384.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01539199985563755,0.040031999349594116,0.0212032001465559,0.01649599988013506,0.008068547381446682,0.0,0.0,0.0,0.0,0.0,0.06588800251483917,0.07897599786520004,0.0703904002904892,0.0703904002904892,0.004214826869769361,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014495999552309513,0.022495999932289124,0.016006399970501663,0.01515199989080429,0.002265581884342885,0.0,0.0,0.0,0.0,0.0,0.1231679990887642,0.13526399433612823,0.1288223996758461,0.1288223996758461,0.004328976434897094,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014592000283300877,0.023231999948620796,0.01705600004643202,0.016048000194132328,0.002810904312746391,0.0,0.0,0.0,0.0,0.0,0.3158079981803894,0.33129599690437317,0.32348800003528594,0.32348800003528594,0.00417599076136664,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014527999795973301,0.021888000890612602,0.01708160014823079,0.01609600055962801,0.0025289234621475062,0.0,0.0,0.0,0.0,0.0,0.5103679895401001,0.5200319886207581,0.5132320046424866,0.5132320046424866,0.0035759433157749533,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014688000082969666,0.032416000962257385,0.019353600032627583,0.016176000237464905,0.0061458798960684425,0.0,0.0,0.0,0.0,0.0,0.7400320172309875,0.7516480088233948,0.7449311971664427,0.7449311971664427,0.004573461776168607,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,32768.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0144640002399683,0.02006400004029274,0.01573119992390275,0.014992000069469213,0.001654446341262991,0.0,0.0,0.0,0.0,0.0,0.07097599655389786,0.09932799637317657,0.07828159928321837,0.07828159928321837,0.009464602895232642,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,[1],1,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.02319999970495701,0.016883199848234654,0.015775999519973993,0.0026693906156048403,0.0,0.0,0.0,0.0,0.0,0.14176000654697418,0.1598079949617386,0.15063679963350293,0.15063679963350293,0.005741662969679433,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,8,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1]",8,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,8q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01484800036996603,0.03203200176358223,0.022224000189453363,0.02247999981045723,0.005996176183124981,0.0,0.0,0.0,0.0,0.0,0.39180800318717957,0.41046398878097534,0.4003200054168701,0.4003200054168701,0.005552433764307601,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,16,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",16,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,16q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015072000212967396,0.028192000463604927,0.017152000125497578,0.015536000020802021,0.003847486121602065,0.0,0.0,0.0,0.0,0.0,0.6239359974861145,0.6367359757423401,0.6285343945026398,0.6285343945026398,0.004006084286606002,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,32,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",32,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,32q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014879999682307243,0.026688000187277794,0.01718079997226596,0.015488000120967627,0.0037132536813398722,0.0,0.0,0.0,0.0,0.0,0.9141119718551636,0.9721279740333557,0.927455997467041,0.927455997467041,0.02148767779232235,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,64,0,40960.0,False,FLASH_ATTN,False,vllm020_batch_spec,"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]",64,1,1,1.0,True,0.0,0.0,0.0,False,0,0,0,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,64q1s40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014751999638974667,0.047520000487565994,0.028710400220006704,0.0266720000654459,0.010774688401598903,0.06094816381288764,0.06816969726785131,0.0644060660218149,0.0644060660218149,0.002203106589073183,0.087051838094461,0.09736630405680231,0.09199073574791852,0.09199073574791852,0.0031466818046499644,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,9,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,520,,,,,,,,False,,,512,BF16,generic,none,CUDA_EVENT,True,[512],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,8,8,9,8,16384.0,0.1111111111111111,q512_8q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.014911999925971031,0.02489599958062172,0.017427200078964235,0.01595200039446354,0.003071906489592143,0.19733789497223914,0.2016295616652644,0.19860388994013833,0.19860388994013833,0.001512389485439305,0.44861409134062713,0.45837046456077934,0.45149211526120153,0.45149211526120153,0.0034381598874302305,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1040,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,16,16,17,16,16384.0,0.058823529411764705,q1k_16q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.015039999969303608,0.03046399913728237,0.020643199887126686,0.016944000497460365,0.006320148675595729,0.2157924314537054,0.22215709640166995,0.21769400765743155,0.21769400765743155,0.0019679921844645526,0.4905115822753901,0.5049789194903589,0.4948340005651485,0.4948340005651485,0.0044733865493072344,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]",1,32,32,33,32,16384.0,0.030303030303030304,q2k_32q1s16k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.017152000218629837,0.02425600029528141,0.01865920014679432,0.018112000077962875,0.0019454553198986453,0.7430866512973927,0.7578834738720781,0.7455351005236347,0.7455351005236347,0.00416692487556653,0.7369773831645824,0.7516525540362471,0.7394057025273603,0.7394057025273603,0.004132666607961175,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,17,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,4112,,,,,,,,False,,,4096,BF16,generic,none,CUDA_EVENT,True,[4096],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,16,16,17,16,32768.0,0.058823529411764705,q4k_16q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.015263999812304974,0.02470399998128414,0.018009600043296815,0.01657600048929453,0.0031544532774534346,0.25251173919752334,0.25566890792461106,0.2536729054481981,0.2536729054481981,0.0010279562245342983,1.0425282722084215,1.0555630628624373,1.0473223013846877,1.0473223013846877,0.004244053880724073,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,33,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,2080,,,,,,,,False,,,2048,BF16,generic,none,CUDA_EVENT,True,[2048],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,32,32,33,32,32768.0,0.030303030303030304,q2k_32q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.01500799972563982,0.027807999402284622,0.01912960009649396,0.01643200032413006,0.004688164695934997,0.1251379565220268,0.14341821167748953,0.12742497577885914,0.12742497577885914,0.005353812167343766,1.1355340167064276,1.3014137556763312,1.1562870179154463,1.1562870179154463,0.048581869194943325,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,65,0,0,True,FLASH_ATTN,False,true_mixed_fused_projected,,1088,,,,,,,,False,,,1024,BF16,generic,none,CUDA_EVENT,True,[1024],[0],"[32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768]",1,64,64,65,64,32768.0,0.015384615384615385,q1k_64q1s32k,fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
0.0,0.0,0.0,0.0,0.0,0.07446400076150894,0.08246400207281113,0.07736000046133995,0.07713599875569344,0.002301031358835964,11.935359954833984,12.102368354797363,11.96896333694458,11.96896333694458,0.05162549713370252,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,8192.0,16384.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07664000242948532,0.08118399977684021,0.07796800062060356,0.077504001557827,0.0013681081693640953,19.84774398803711,20.15795135498047,19.915702438354494,19.915702438354494,0.0912299324030902,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,16384.0,24576.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks24k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0753600001335144,0.08207999914884567,0.07715519964694977,0.07595199719071388,0.0024238358447475007,27.781503677368164,27.9836483001709,27.844886589050287,27.844886589050287,0.061307010154819624,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,24576.0,32768.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04339199885725975,0.050016000866889954,0.04504639990627766,0.04391999915242195,0.002339637813151782,5.1544318199157715,5.269279956817627,5.16938238143921,5.16938238143921,0.03363105774712194,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,4096,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,8192.0,12288.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks12k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04291199892759323,0.058848001062870026,0.045657599717378615,0.04383999854326248,0.004522763233004815,9.256383895874023,9.27734375,9.261776161193849,9.261776161193849,0.0062232312957398745,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,4096,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,16384.0,20480.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks20k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.043296001851558685,0.04982399940490723,0.045123199746012685,0.04387199878692627,0.0023369398894319345,13.365216255187988,13.634464263916016,13.398719978332519,13.398719978332519,0.0787651922310212,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,4096,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,24576.0,28672.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks28k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02703999914228916,0.0297279991209507,0.027692800015211107,0.02723200060427189,0.000851127720159845,2.387968063354492,2.4014720916748047,2.3920736074447637,2.3920736074447637,0.003552645719470337,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,2048,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,8192.0,10240.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks10k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02691200003027916,0.029823999851942062,0.027689599990844728,0.027583999559283257,0.0007783369959809023,4.440767765045166,4.4521918296813965,4.444268751144409,4.444268751144409,0.004022325406840951,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,2048,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,16384.0,18432.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks18k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02703999914228916,0.03888000175356865,0.030262400023639204,0.02801600005477667,0.0037877256209144718,6.500351905822754,6.600607872009277,6.524902391433716,6.524902391433716,0.03321667087212851,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,2048,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,24576.0,26624.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks26k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07865600287914276,0.08668799698352814,0.08130879923701287,0.07993599772453308,0.0027016201268628523,35.717376708984375,35.843265533447266,35.771837615966795,35.771837615966795,0.04024815379149301,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,40960,1,8192,32768.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,32768.0,40960.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04179200157523155,0.04864000156521797,0.0436256006360054,0.04267200082540512,0.002191476789190783,6.103871822357178,6.18287992477417,6.118390369415283,6.118390369415283,0.022924175047267112,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,8192.0,16384.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04163200035691261,0.05987200140953064,0.04625920057296753,0.04403200000524521,0.005544136325859629,10.207136154174805,11.073247909545898,10.326777648925782,10.326777648925782,0.25139335734700863,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,16384.0,24576.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks24k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04137599840760231,0.05027199909090996,0.04355199970304966,0.042399998754262924,0.0026572716942034787,14.303423881530762,14.343520164489746,14.311049747467042,14.311049747467042,0.01137511287661936,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,24576.0,32768.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.026016000658273697,0.03718400001525879,0.03212799951434135,0.03270399942994118,0.003953184738275612,2.6534719467163086,2.6875839233398438,2.661257576942444,2.661257576942444,0.009372641904054613,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,4096,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,8192.0,12288.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks12k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.025887999683618546,0.03347200155258179,0.027168000116944313,0.02649599965661764,0.0021492000999850562,4.70630407333374,4.7400641441345215,4.714492845535279,4.714492845535279,0.009349196197962609,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,4096,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,16384.0,20480.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks20k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.025631999596953392,0.030719999223947525,0.02736639976501465,0.02711999975144863,0.0013921874495504173,6.759712219238281,6.831999778747559,6.774675178527832,6.774675178527832,0.021507023842020512,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,4096,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,24576.0,28672.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks28k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017855999991297722,0.024831999093294144,0.01991359982639551,0.018655999563634396,0.0023971416189370203,1.3446400165557861,1.3609600067138672,1.3508928060531615,1.3508928060531615,0.006186954712541735,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,2048,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,8192.0,10240.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks10k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0180479995906353,0.022752000018954277,0.019507200084626676,0.01896000001579523,0.0015079573553847933,2.5208001136779785,2.5887041091918945,2.534086418151855,2.534086418151855,0.01891953046799999,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,2048,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,16384.0,18432.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks18k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.018144000321626663,0.03222399950027466,0.02052800003439188,0.018864000216126442,0.004114364828004189,3.6922879219055176,3.760576009750366,3.706630396842957,3.706630396842957,0.019888657921309623,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,2048,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,24576.0,26624.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks26k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04169600084424019,0.04822399839758873,0.0439775999635458,0.04334400035440922,0.002101844179466219,18.41494369506836,18.502975463867188,18.445004844665526,18.445004844665526,0.026939913540867878,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,40960,1,8192,32768.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,32768.0,40960.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.023615999147295952,0.03267199918627739,0.026281599886715412,0.0248800003901124,0.003167969318232417,3.1188158988952637,3.1837120056152344,3.133536005020142,3.133536005020142,0.018365009771617643,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,8192.0,16384.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks16k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02380800060927868,0.03283200040459633,0.025670399703085423,0.024639999493956566,0.0026095917641781453,5.1729278564453125,5.243135929107666,5.192828798294067,5.192828798294067,0.01984737475315108,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,16384.0,24576.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks24k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024032000452280045,0.03167999908328056,0.02665280010551214,0.02550400048494339,0.002510131946267113,7.223167896270752,7.257152080535889,7.231532812118529,7.231532812118529,0.009418898846297825,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,24576.0,32768.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks32k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01696000061929226,0.023679999634623528,0.01866880003362894,0.017455999739468098,0.002277860345236006,1.478559970855713,1.496127963066101,1.48257919549942,1.48257919549942,0.005278358037488471,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,4096,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,8192.0,12288.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks12k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017023999243974686,0.030688000842928886,0.02055360022932291,0.018240000121295452,0.004065815389665311,2.651711940765381,2.6691839694976807,2.657548785209656,2.657548785209656,0.005897264516465086,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,4096,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,16384.0,20480.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks20k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.016767999157309532,0.024351999163627625,0.01840319987386465,0.017167999409139156,0.0025234367788448957,3.823551893234253,3.8631999492645264,3.8335999727249135,3.8335999727249135,0.011858923917429712,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,4096,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,24576.0,28672.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks28k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.013952000066637993,0.03622400015592575,0.018214400112628936,0.014719999860972166,0.007277897466521675,0.7039039731025696,0.7163199782371521,0.7077983975410462,0.7077983975410462,0.004048424224033295,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,2048,8192.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,8192.0,10240.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks10k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.015104000456631184,0.03097599931061268,0.020870400313287973,0.02054399996995926,0.005422197456220526,1.2929600477218628,1.313088059425354,1.3006752014160157,1.3006752014160157,0.00790622446009414,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,2048,16384.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,16384.0,18432.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks18k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.03232000023126602,0.019132800027728082,0.01673599984496832,0.0050857949387988245,1.8775999546051025,1.9125759601593018,1.8867840051651,1.8867840051651,0.01196043526228758,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,2048,24576.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,24576.0,26624.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks26k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.023584000766277313,0.03126399964094162,0.02633600030094385,0.025200000032782555,0.0025710957466677864,9.283391952514648,9.48249626159668,9.331705665588379,9.331705665588379,0.06366970422148335,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,40960,1,8192,32768.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,32768.0,40960.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks40k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07552000135183334,0.0851840004324913,0.07839040011167527,0.07703999802470207,0.0030805904904383677,43.62025451660156,43.89299011230469,43.68390693664551,43.68390693664551,0.08458163192147439,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,40960.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,40960.0,49152.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks48k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07718399912118912,0.0854400023818016,0.07895359992980958,0.07791999727487564,0.0024425064759109735,59.421791076660156,59.73017501831055,59.5021312713623,59.5021312713623,0.10367381308510447,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,57344.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,57344.0,65536.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks64k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07875200361013412,0.09055999666452408,0.08208959847688675,0.08087999746203423,0.0033614630055883482,75.2852783203125,75.55481719970703,75.38758392333985,75.38758392333985,0.08870109119325344,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,73728.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,73728.0,81920.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks80k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07788799703121185,0.09888000041246414,0.0819871999323368,0.08008000254631042,0.005835618489111142,91.13442993164062,91.45164489746094,91.24225158691405,91.24225158691405,0.1009018902177725,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,90112.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,90112.0,98304.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks96k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07596799731254578,0.08790399879217148,0.07967040091753005,0.07808000221848488,0.0036209252740976605,106.89055633544922,107.34063720703125,106.9560287475586,106.9560287475586,0.13032874360676439,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,106496.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,106496.0,114688.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks112k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07648000121116638,0.08534400165081024,0.07928640022873878,0.07787200063467026,0.0028305104107121735,122.71724700927734,122.9840316772461,122.8334243774414,122.8334243774414,0.09625274868603513,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,122880.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,122880.0,131072.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.07664000242948532,0.08774399757385254,0.08081279993057251,0.07972799986600876,0.003487270970977775,130.6565399169922,131.09359741210938,130.79229431152345,130.79229431152345,0.13138911961272914,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,8192,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,131072.0,139264.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks136k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.01532800029963255,0.040063999593257904,0.019459199998527764,0.01601599995046854,0.007496165774486326,9.443936347961426,9.649087905883789,9.489968109130858,9.489968109130858,0.05961646816296781,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,512,130560.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,130560.0,131072.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02691200003027916,0.040832001715898514,0.02942080032080412,0.027888000011444092,0.004040048279091587,16.753759384155273,16.90662384033203,16.78766403198242,16.78766403198242,0.04236470233451937,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,2048,65536.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,65536.0,67584.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks66k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04416000097990036,0.04867200180888176,0.04565120078623295,0.04468800127506256,0.0018079971851529544,50.29715347290039,50.50300979614258,50.35054740905761,50.35054740905761,0.0724480602714254,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,4096,98304.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,98304.0,102400.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks100k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.060447998344898224,0.06684800237417221,0.06276160031557083,0.061824001371860504,0.0024045636532566625,96.07142639160156,96.53209686279297,96.1898666381836,96.1898666381836,0.1365794879996899,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,1,147456,1,6144,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[6144],6144,6144,6144,6144.0,True,0.0,0.0,0.0,True,131072.0,137216.0,6144,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q6ks134k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04217600077390671,0.05100800096988678,0.04406719990074635,0.042847998440265656,0.002656672983576728,22.5166072845459,22.986656188964844,22.63068161010742,22.63068161010742,0.13840494695459715,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,40960.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,40960.0,49152.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks48k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04182400181889534,0.047200001776218414,0.043644800409674646,0.04262400045990944,0.001927741871473188,30.725727081298828,30.787456512451172,30.74285774230957,30.74285774230957,0.019110324860515015,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,57344.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,57344.0,65536.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks64k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04185599833726883,0.05049600079655647,0.043852799385786054,0.04289599880576134,0.0024573088797598033,38.930206298828125,38.98448181152344,38.94538269042969,38.94538269042969,0.017734743323340796,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,73728.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,73728.0,81920.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks80k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04227200150489807,0.046911999583244324,0.04412479996681214,0.04327999986708164,0.001811858548765738,47.13151931762695,47.245887756347656,47.148198699951166,47.148198699951166,0.033297799765613076,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,90112.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,90112.0,98304.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks96k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04182400181889534,0.06195199862122536,0.04529919996857643,0.043136000633239746,0.005751677082163394,55.338497161865234,55.64672088623047,55.42207336425782,55.42207336425782,0.11010194068839292,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,106496.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,106496.0,114688.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks112k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.04182400181889534,0.054687999188899994,0.04418559968471527,0.042767999693751335,0.0036820249064621804,63.549087524414055,63.80697631835938,63.62084197998047,63.62084197998047,0.08872184973119365,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,122880.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,122880.0,131072.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.0461760014295578,0.06566400080919266,0.05008000023663044,0.04843199998140335,0.0055350567765421,67.64147186279297,67.91651153564453,67.70619888305666,67.70619888305666,0.0993520482760623,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,8192,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,131072.0,139264.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks136k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.023711999878287315,0.03859199956059456,0.02689919974654913,0.0244159996509552,0.004626699769228834,4.775519847869873,4.829855918884277,4.790303993225097,4.790303993225097,0.01597276061319242,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,512,130560.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,130560.0,131072.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024224000051617622,0.0453759990632534,0.027676799893379213,0.025200000032782555,0.006154880946840619,9.579392433166504,9.63871955871582,9.59802885055542,9.59802885055542,0.016811667352984866,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,2048,65536.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,65536.0,67584.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks66k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02630399912595749,0.03593600168824196,0.02780479993671179,0.027040000073611736,0.0027569987978884785,25.21686363220215,25.383039474487305,25.250255966186526,25.250255966186526,0.04761963064809279,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,4096,98304.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,98304.0,102400.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks100k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.034015998244285583,0.041728001087903976,0.03665280006825924,0.0352960005402565,0.002710617869728372,48.101280212402344,48.49884796142578,48.17219200134278,48.17219200134278,0.11195495368044632,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,2,147456,1,6144,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[6144],6144,6144,6144,6144.0,True,0.0,0.0,0.0,True,131072.0,137216.0,6144,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q6ks134k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024191999807953835,0.039583999663591385,0.027286400087177753,0.025200000032782555,0.004620118437533604,11.32140827178955,11.496224403381348,11.354345512390138,11.354345512390138,0.050117766215439966,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,40960.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,40960.0,49152.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks48k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024032000452280045,0.03232000023126602,0.026406400091946124,0.02518399991095066,0.002792696117638337,15.42249584197998,15.639776229858397,15.451993656158448,15.451993656158448,0.06304729308178388,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,57344.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,57344.0,65536.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks64k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024224000051617622,0.03488000109791756,0.026147199980914592,0.02459200005978346,0.003303059079404486,19.5251522064209,19.70569610595703,19.54985942840576,19.54985942840576,0.052248914965338324,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,73728.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,73728.0,81920.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks80k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024159999564290047,0.03046399913728237,0.0255103999748826,0.024656000547111034,0.00195717586616911,23.630016326904297,23.927040100097656,23.672822570800783,23.672822570800783,0.08715594728873713,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,90112.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,90112.0,98304.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks96k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02380800060927868,0.03574400022625923,0.02678720001131296,0.024720000103116035,0.003678231234048846,27.736671447753906,27.79840087890625,27.747158622741697,27.747158622741697,0.018952179343788657,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,106496.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,106496.0,114688.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks112k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.024224000051617622,0.042080000042915344,0.02844479978084564,0.02527999971061945,0.006562862750709003,31.83427238464356,32.08835220336914,31.86994876861572,31.86994876861572,0.07444245241186317,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,122880.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,122880.0,131072.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.02377600036561489,0.03139200061559677,0.026396799832582474,0.025071999989449978,0.0025962810796740263,33.88313674926758,33.96985626220703,33.89708137512208,33.89708137512208,0.02518493598134421,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,8192,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[8192],8192,8192,8192,8192.0,True,0.0,0.0,0.0,True,131072.0,139264.0,8192,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q8ks136k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014944000169634819,0.022624000906944275,0.017174400109797715,0.015536000020802021,0.0028331860349340154,3.179744005203247,3.192960023880005,3.182867193222046,3.182867193222046,0.0035239767128429386,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,512,130560.0,True,FLASH_ATTN,False,vllm020_batch_spec,[512],512,512,512,512.0,True,0.0,0.0,0.0,True,130560.0,131072.0,512,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q512s128k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.014655999839305878,0.02985600009560585,0.017318400088697672,0.015568000264465809,0.004479309643844885,4.811935901641846,4.826848030090332,4.8173023700714115,4.8173023700714115,0.00594674080057053,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,2048,65536.0,True,FLASH_ATTN,False,vllm020_batch_spec,[2048],2048,2048,2048,2048.0,True,0.0,0.0,0.0,True,65536.0,67584.0,2048,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q2ks66k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.017184000462293625,0.03916800022125244,0.021356799826025962,0.01935999933630228,0.0062801287963799276,14.374591827392578,14.635007858276367,14.41227512359619,14.41227512359619,0.07569270440104603,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,4096,98304.0,True,FLASH_ATTN,False,vllm020_batch_spec,[4096],4096,4096,4096,4096.0,True,0.0,0.0,0.0,True,98304.0,102400.0,4096,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q4ks100k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
0.0,0.0,0.0,0.0,0.0,0.020479999482631683,0.033215999603271484,0.023340800032019614,0.02092800009995699,0.004304974035052475,24.088096618652344,24.18492889404297,24.11243553161621,24.11243553161621,0.02797845886790172,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2048,32,4,16,4,147456,1,6144,131072.0,True,FLASH_ATTN,False,vllm020_batch_spec,[6144],6144,6144,6144,6144.0,True,0.0,0.0,0.0,True,131072.0,137216.0,6144,BF16,generic,none,CUDA_EVENT,False,,,,,,,,,,,q6ks134k,measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
1 time_stats.attn_input_reshape.min time_stats.attn_input_reshape.max time_stats.attn_input_reshape.mean time_stats.attn_input_reshape.median time_stats.attn_input_reshape.std time_stats.attn_kv_cache_save.min time_stats.attn_kv_cache_save.max time_stats.attn_kv_cache_save.mean time_stats.attn_kv_cache_save.median time_stats.attn_kv_cache_save.std time_stats.attn_prefill.min time_stats.attn_prefill.max time_stats.attn_prefill.mean time_stats.attn_prefill.median time_stats.attn_prefill.std time_stats.attn_decode.min time_stats.attn_decode.max time_stats.attn_decode.mean time_stats.attn_decode.median time_stats.attn_decode.std time_stats.attn_output_reshape.min time_stats.attn_output_reshape.max time_stats.attn_output_reshape.mean time_stats.attn_output_reshape.median time_stats.attn_output_reshape.std n_embd n_q_head n_kv_head block_size num_tensor_parallel_workers max_model_len batch_size prefill_chunk_size kv_cache_size is_prefill attention_backend is_mixed_batch mode seq_lens total_tokens max_seq_len min_seq_len avg_seq_len equal_seq_len seq_len_variance seq_len_std seq_len_cv is_chunked_prefill_sample chunk_start_token chunk_end_token total_prefill_tokens profiling_precision model_arch quant_signature measurement_type is_true_mixed_batch prefill_seq_lens prefill_kv_cache_sizes decode_kv_cache_sizes num_prefill_seqs num_decode_seqs decode_batch_size total_batch_size total_decode_tokens decode_avg_kv_cache_size batch_composition_ratio batch_spec projection_policy
2 0.0 0.0 0.0 0.0 0.0 0.01414399966597557 0.028863999992609024 0.019705599918961526 0.01771199982613325 0.005157200849836681 0.047968000173568726 0.07046400010585785 0.05810240097343922 0.05810240097343922 0.007477463486041561 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 64 0.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 False 0.0 64.0 64 BF16 generic none CUDA_EVENT False q64 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
3 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.04947200044989586 0.020412799902260303 0.01635199971497059 0.010107497379722417 0.046560000628232956 0.08323200047016144 0.05587520003318787 0.05587520003318787 0.011126758739503428 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 128 0.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 False 0.0 128.0 128 BF16 generic none CUDA_EVENT False q128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
4 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.022207999601960182 0.017033600155264138 0.015312000177800655 0.002819235991970241 0.05104000121355057 0.07692799717187881 0.056396800279617305 0.056396800279617305 0.007481982178637539 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 256 0.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 False 0.0 256.0 256 BF16 generic none CUDA_EVENT False q256 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
5 0.0 0.0 0.0 0.0 0.0 0.015072000212967396 0.022272000089287758 0.01706880023702979 0.01616000011563301 0.002460889579319197 0.06931199878454208 0.0838719978928566 0.07432000041007995 0.07432000041007995 0.004777766433175866 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 512 0.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 False 0.0 512.0 512 BF16 generic none CUDA_EVENT False q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
6 0.0 0.0 0.0 0.0 0.0 0.018592000007629395 0.028543999418616295 0.02095999978482723 0.019183999858796597 0.003198175496053494 0.12179200351238251 0.15408000349998474 0.1307712011039257 0.1307712011039257 0.00858807797538298 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False q1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
7 0.0 0.0 0.0 0.0 0.0 0.027775999158620834 0.03385600075125694 0.030131200328469276 0.029680000618100166 0.0021152558103575215 0.32678401470184326 0.3450239896774292 0.33396480381488797 0.33396480381488797 0.0045872424917606375 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
8 0.0 0.0 0.0 0.0 0.0 0.04438399896025658 0.05084799975156784 0.046540799736976626 0.04531199857592583 0.002277905811237223 1.0959680080413818 1.1151360273361206 1.0999775886535645 1.0999775886535645 0.005694403246120485 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False q4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
9 0.0 0.0 0.0 0.0 0.0 0.078015998005867 0.08691199868917465 0.08114239946007729 0.08019199967384338 0.00292795706334475 4.070400238037109 4.113152027130127 4.087088012695312 4.087088012695312 0.013660567012509554 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False q8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
10 0.0 0.0 0.0 0.0 0.0 0.016063999384641647 0.05167999863624573 0.022115200012922286 0.017583999782800674 0.010340094822340818 0.05196800082921982 0.09011200070381165 0.06328320093452933 0.06328320093452933 0.012557341255467452 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 64 448.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 True 448.0 512.0 64 BF16 generic none CUDA_EVENT False q64s512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
11 0.0 0.0 0.0 0.0 0.0 0.01583999954164028 0.026623999699950218 0.018927999772131443 0.017376000061631203 0.003514650316260619 0.06681600213050842 0.07993599772453308 0.0725280001759529 0.0725280001759529 0.004343502558613716 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 128 896.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 True 896.0 1024.0 128 BF16 generic none CUDA_EVENT False q128s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
12 0.0 0.0 0.0 0.0 0.0 0.01648000068962574 0.030880000442266464 0.01945280022919178 0.017967999912798405 0.004096211183007485 0.1311360001564026 0.1546880006790161 0.13908160030841826 0.13908160030841826 0.007511906874366178 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 256 1792.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 True 1792.0 2048.0 256 BF16 generic none CUDA_EVENT False q256s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
13 0.0 0.0 0.0 0.0 0.0 0.017855999991297722 0.03558399900794029 0.020851199887692927 0.018559999763965607 0.005235911594130716 0.32950401306152344 0.350271999835968 0.33912960588932034 0.33912960588932034 0.006027400986663648 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 512 3584.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 3584.0 4096.0 512 BF16 generic none CUDA_EVENT False q512s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
14 0.0 0.0 0.0 0.0 0.0 0.019328000023961067 0.040608000010252 0.022790400311350822 0.020704000256955624 0.006113051965778337 1.1415679454803467 1.1518720388412476 1.144483208656311 1.144483208656311 0.0032332311374389127 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 1024 7168.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 True 7168.0 8192.0 1024 BF16 generic none CUDA_EVENT False q1ks8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
15 0.0 0.0 0.0 0.0 0.0 0.015807999297976494 0.030688000842928886 0.019596799835562707 0.01774400006979704 0.004343384771033462 0.0 0.0 0.0 0.0 0.0 0.049056001007556915 0.07580800354480743 0.05948160067200661 0.05948160067200661 0.009031541471446955 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
16 0.0 0.0 0.0 0.0 0.0 0.01603199914097786 0.02486399933695793 0.01923839971423149 0.018079999834299088 0.0032282528537266424 0.0 0.0 0.0 0.0 0.0 0.05142400041222572 0.07353600114583969 0.059328000620007516 0.059328000620007516 0.0073307807735143084 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
17 0.0 0.0 0.0 0.0 0.0 0.016543999314308167 0.03977600112557411 0.021379199624061585 0.018511999398469925 0.006593576176246171 0.0 0.0 0.0 0.0 0.0 0.0488319993019104 0.06435199826955795 0.05479039996862411 0.05479039996862411 0.005672522998491864 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
18 0.0 0.0 0.0 0.0 0.0 0.01635199971497059 0.02844800055027008 0.019267200119793416 0.017952000722289085 0.0035068687666949577 0.0 0.0 0.0 0.0 0.0 0.049855999648571014 0.07798399776220322 0.05986879989504815 0.05986879989504815 0.01043914754878828 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
19 0.0 0.0 0.0 0.0 0.0 0.016383999958634377 0.026079999282956123 0.01923519968986511 0.017791999503970146 0.0032161974331284568 0.0 0.0 0.0 0.0 0.0 0.058111999183893204 0.1045759990811348 0.06708480007946492 0.06708480007946492 0.013479022462646494 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
20 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.04057599976658821 0.019100800156593323 0.015455999877303839 0.007512281243011577 0.0 0.0 0.0 0.0 0.0 0.05363199859857559 0.07782399654388428 0.06090559959411622 0.06090559959411622 0.007544620176348091 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
21 0.0 0.0 0.0 0.0 0.0 0.014431999996304512 0.02191999927163124 0.016684799920767546 0.01563199982047081 0.0024293118621811216 0.0 0.0 0.0 0.0 0.0 0.0629120022058487 0.07891199737787247 0.06891520097851753 0.06891520097851753 0.005472695665695425 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
22 0.0 0.0 0.0 0.0 0.0 0.014560000039637089 0.038943998515605927 0.018313600029796363 0.01561600062996149 0.007127270260115769 0.0 0.0 0.0 0.0 0.0 0.08675199747085571 0.10662399977445602 0.09391999915242194 0.09391999915242194 0.006988099589086635 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
23 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.054687999188899994 0.021439999900758268 0.01539199985563755 0.012052764849597775 0.0 0.0 0.0 0.0 0.0 0.13488000631332397 0.1528639942407608 0.1431359991431236 0.1431359991431236 0.005436271464033599 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
24 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.041919998824596405 0.01899839974939823 0.015343999955803156 0.007989843526623287 0.0 0.0 0.0 0.0 0.0 0.06176000088453293 0.08374399691820145 0.06747519969940186 0.06747519969940186 0.0066067747128778 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
25 0.0 0.0 0.0 0.0 0.0 0.016256000846624374 0.11353600025177002 0.042761600017547606 0.028960000723600388 0.029104301538020762 0.0 0.0 0.0 0.0 0.0 0.09734400361776352 0.14422400295734406 0.11392960175871848 0.11392960175871848 0.013198594600417867 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
26 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.034143999218940735 0.018918400071561335 0.01643200032413006 0.005500943993080684 0.0 0.0 0.0 0.0 0.0 0.12918399274349213 0.15087999403476715 0.13807999789714814 0.13807999789714814 0.007658330538677587 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
27 0.0 0.0 0.0 0.0 0.0 0.016063999384641647 0.03641600161790848 0.0198208000510931 0.01780799962580204 0.0057264128169845765 0.0 0.0 0.0 0.0 0.0 0.22099199891090393 0.23904000222682953 0.2293503984808922 0.2293503984808922 0.004861342907006028 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
28 0.0 0.0 0.0 0.0 0.0 0.014751999638974667 0.035840000957250595 0.018908800091594458 0.015792000107467175 0.0064374817924757475 0.0 0.0 0.0 0.0 0.0 0.10134399682283401 0.12201599776744843 0.10896319895982742 0.10896319895982742 0.006336330809165179 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
29 0.0 0.0 0.0 0.0 0.0 0.013856000266969204 0.03417599946260452 0.017846399918198586 0.014800000004470348 0.006495007539635255 0.0 0.0 0.0 0.0 0.0 0.13126400113105774 0.15561600029468536 0.1389280006289482 0.1389280006289482 0.008381472811075022 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
30 0.0 0.0 0.0 0.0 0.0 0.014431999996304512 0.03519999980926514 0.019168000388890504 0.01600000075995922 0.005995522477654695 0.0 0.0 0.0 0.0 0.0 0.21728000044822693 0.2343679964542389 0.2231455981731415 0.2231455981731415 0.004720730646739123 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
31 0.0 0.0 0.0 0.0 0.0 0.014047999866306782 0.03670400008559227 0.018441599886864425 0.015023999847471714 0.006596535162793127 0.0 0.0 0.0 0.0 0.0 0.39321601390838623 0.4524799883365631 0.4058080047369003 0.4058080047369003 0.01578349755088941 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
32 0.0 0.0 0.0 0.0 0.0 0.014336000196635723 0.022143999114632607 0.016912000067532063 0.015168000012636185 0.0028156089295136347 0.0 0.0 0.0 0.0 0.0 0.15587200224399567 0.3079040050506592 0.17838079929351805 0.17838079929351805 0.04355865575265927 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
33 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.02112000063061714 0.015516800060868263 0.01488000014796853 0.001940870731593904 0.0 0.0 0.0 0.0 0.0 0.21587200462818146 0.23561599850654602 0.22250880002975468 0.22250880002975468 0.006181951170646666 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
34 0.0 0.0 0.0 0.0 0.0 0.015552000142633915 0.039264000952243805 0.023609600123018028 0.02131200022995472 0.007236979625711548 0.0 0.0 0.0 0.0 0.0 0.408735990524292 0.470335990190506 0.4336863994598388 0.4336863994598388 0.01844662383160074 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
35 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.025407999753952026 0.016227199975401164 0.014960000291466713 0.0031617375441736185 0.0 0.0 0.0 0.0 0.0 0.7412800192832947 0.7627840042114258 0.7464000046253203 0.7464000046253203 0.006112167448837547 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
36 0.0 0.0 0.0 0.0 0.0 0.01462399959564209 0.02812799997627735 0.020652799773961304 0.021359999664127827 0.004308706957613102 0.028383498565450627 0.039859687970646644 0.032492258074592426 0.032492258074592426 0.00453597266208597 0.029312501176103633 0.04116431058787463 0.03355574193327539 0.03355574193327539 0.004684436757701648 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 72 False 64 BF16 generic none CUDA_EVENT True [64] [0] [512, 512, 512, 512, 512, 512, 512, 512] 1 8 8 9 8 512.0 0.1111111111111111 q64_8q1s512 fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
37 0.0 0.0 0.0 0.0 0.0 0.015552000142633915 0.034143999218940735 0.023171199765056372 0.024255999363958836 0.005908614918096971 0.03333159243114438 0.038935341782478095 0.03580428402241854 0.03580428402241854 0.002082270297044095 0.03633240903369937 0.04244065945634484 0.03902771507087562 0.03902771507087562 0.0022697354261490147 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 136 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 8 8 9 8 1024.0 0.1111111111111111 q128_8q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
38 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.02611199952661991 0.019635199941694735 0.018112000077962875 0.0038298050749257795 0.04189529417991216 0.057484239920526384 0.04744885718421094 0.04744885718421094 0.004779830748455743 0.051672703037266184 0.07089975418195164 0.05852234134479412 0.05852234134479412 0.005895334539786378 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 144 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 16 16 17 16 1024.0 0.058823529411764705 q128_16q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
39 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.029311999678611755 0.018662399891763926 0.01673599984496832 0.0044017112162725355 0.04322973959325901 0.05049827064705393 0.04535414343408448 0.04535414343408448 0.0022944156000240697 0.08733025617719538 0.10201372836398578 0.09162185574241775 0.09162185574241775 0.004635047631846023 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 272 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 16 16 17 16 2048.0 0.058823529411764705 q256_16q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
40 0.0 0.0 0.0 0.0 0.0 0.014592000283300877 0.026367999613285065 0.016336000058799982 0.01515199989080429 0.003415353455946402 0.06031842775160765 0.06618323188375198 0.06274415549817247 0.06274415549817247 0.001985647289644255 0.14768157653992678 0.16204076249052324 0.15362064543185072 0.15362064543185072 0.004861590945216247 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 288 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 32 32 33 32 2048.0 0.030303030303030304 q256_32q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
41 0.0 0.0 0.0 0.0 0.0 0.014751999638974667 0.02454400062561035 0.017167999967932702 0.016191999427974224 0.0028685016454498436 0.09128700688359712 0.09689150775996329 0.09360396051475776 0.09360396051475776 0.0013477542744916764 0.2740889887523892 0.2909164873209846 0.2810456356995366 0.2810456356995366 0.004046628526808561 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 544 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q512_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
42 0.0 0.0 0.0 0.0 0.0 0.01881599985063076 0.03097599931061268 0.024598400108516216 0.024848000146448612 0.0037539437391565975 0.1035249255866932 0.10603132147437412 0.10399797220840973 0.10399797220840973 0.0007025109429056814 0.5652750707893444 0.5789606938874117 0.5678580377517648 0.5678580377517648 0.003835906384194897 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 576 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 64 64 65 64 4096.0 0.015384615384615385 q512_64q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
43 0.0 0.0 0.0 0.0 0.0 0.018624000251293182 0.043487999588251114 0.024460799992084503 0.019600000232458115 0.008922081629781394 0.196169204945307 0.2076140047945799 0.2008444429250931 0.2008444429250931 0.00394350953292805 1.1196708009293268 1.1849940417370974 1.1463555573610091 1.1463555573610091 0.022508285530529783 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192] 1 64 64 65 64 8192.0 0.015384615384615385 q1k_64q1s8k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
44 0.0 0.0 0.0 0.0 0.0 0.027135999873280525 0.03667199984192848 0.02945920005440712 0.028256000019609928 0.0029446678408169553 0.37757279619664613 0.3898113624476372 0.38075520430942184 0.38075520430942184 0.0036600203831042254 0.2522831942132049 0.2604606493092597 0.25440958703617433 0.25440958703617433 0.0024455194930253126 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q2k_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
45 0.0 0.0 0.0 0.0 0.0 0.0435199998319149 0.049695998430252075 0.04502719938755036 0.04395199939608574 0.002035785660169308 1.1048984388245497 1.1189053886476108 1.1112371236754128 1.1112371236754128 0.0050220696724624985 0.1395495077239122 0.14131859607071193 0.14035008841031085 0.14035008841031085 0.0006342911944856293 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 16 16 17 16 4096.0 0.058823529411764705 q4k_16q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
46 0.0 0.0 0.0 0.0 0.0 0.018783999606966972 0.024288000538945198 0.020627199858427047 0.019567999988794327 0.0019457052717059358 0.09455999732017517 0.12185599654912949 0.10207359939813614 0.10207359939813614 0.00753346544014261 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 2 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512] 1024 512 512 512.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False 2q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
47 0.0 0.0 0.0 0.0 0.0 0.027295999228954315 0.034752000123262405 0.02943360023200512 0.028528000228106976 0.0023159160681123767 0.14416000247001648 0.15904000401496887 0.14979200065135959 0.14979200065135959 0.00480624675866005 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 4 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512] 2048 512 512 512.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False 4q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
48 0.0 0.0 0.0 0.0 0.0 0.043455999344587326 0.05084799975156784 0.045500800386071204 0.04411200061440468 0.002490556062831049 0.24454399943351746 0.25865599513053894 0.2504959970712662 0.2504959970712662 0.003778494140301353 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512] 4096 512 512 512.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 8q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
49 0.0 0.0 0.0 0.0 0.0 0.07673600316047668 0.08374399691820145 0.07970559895038605 0.07873599976301193 0.0022907976135004057 0.445248007774353 0.4758400022983551 0.45409599840641024 0.45409599840641024 0.009133230340383306 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512] 8192 512 512 512.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 16q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
50 0.0 0.0 0.0 0.0 0.0 0.043296001851558685 0.051072001457214355 0.044972800090909 0.04399999976158142 0.002451216824441962 0.6147199869155884 0.6290879845619202 0.6204927921295166 0.6204927921295166 0.004344846739788608 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 2 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048] 4096 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 2q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
51 0.0 0.0 0.0 0.0 0.0 0.07737600058317184 0.09123200178146362 0.08094720020890236 0.07980800047516823 0.004065264798368611 1.1744320392608643 1.1887680292129517 1.178323209285736 1.178323209285736 0.004395876469319665 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 4 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048, 2048, 2048] 8192 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 4q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
52 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.03254399821162224 0.01810879958793521 0.01611199975013733 0.005058478889747962 0.0 0.0 0.0 0.0 0.0 0.06339199841022491 0.0841279998421669 0.07019519805908202 0.07019519805908202 0.006070126182471763 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
53 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.030271999537944794 0.018124799989163876 0.015711999498307705 0.004696400814632773 0.0 0.0 0.0 0.0 0.0 0.2739199995994568 0.2922239899635315 0.28281279802322384 0.28281279802322384 0.00633037978599564 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
54 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.022431999444961548 0.016844799742102623 0.015471999999135733 0.0027624803153841917 0.0 0.0 0.0 0.0 0.0 0.3909119963645935 0.4160960018634796 0.39996159672737125 0.39996159672737125 0.007037174636804898 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
55 0.0 0.0 0.0 0.0 0.0 0.014240000396966934 0.035071998834609985 0.018764800019562246 0.015583999920636415 0.006305594700523817 0.0 0.0 0.0 0.0 0.0 0.7383679747581482 0.7597119808197021 0.7430047929286957 0.7430047929286957 0.006192645960911466 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
56 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.028991999104619026 0.019401599932461978 0.01665600063279271 0.005434953793780546 0.0 0.0 0.0 0.0 0.0 1.427008032798767 1.4517120122909546 1.4361984014511109 1.4361984014511109 0.008802755821028187 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
57 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.02844800055027008 0.01820160010829568 0.014944000169634819 0.004942002036909087 0.0 0.0 0.0 0.0 0.0 0.08361600339412689 0.11027199774980545 0.09058240056037903 0.09058240056037903 0.00872938604423622 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
58 0.0 0.0 0.0 0.0 0.0 0.014112000353634357 0.023104000836610794 0.01648960020393133 0.015632000286132097 0.0027628828340349578 0.0 0.0 0.0 0.0 0.0 0.5063040256500244 0.5497599840164185 0.5168287932872773 0.5168287932872773 0.013557229606313293 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
59 0.0 0.0 0.0 0.0 0.0 0.01616000011563301 0.029055999591946602 0.018780799955129622 0.017215999774634838 0.003794434947431941 0.0 0.0 0.0 0.0 0.0 0.7439360022544861 0.7719680070877075 0.7502080142498017 0.7502080142498017 0.00839205598262567 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
60 0.0 0.0 0.0 0.0 0.0 0.015968000516295433 0.03046399913728237 0.018822400271892546 0.01726400014013052 0.004212536831927695 0.0 0.0 0.0 0.0 0.0 1.4256000518798828 1.449504017829895 1.4325888037681578 1.4325888037681578 0.0065448028108711165 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
61 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.027712000533938408 0.01633920017629862 0.014944000169634819 0.0038488220071983326 0.0 0.0 0.0 0.0 0.0 2.798719882965088 3.0184640884399414 2.8293471813201903 2.8293471813201903 0.06375662767704417 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
62 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.021407999098300934 0.01637439979240298 0.014992000069469213 0.0024463594774459265 0.0 0.0 0.0 0.0 0.0 0.09347199648618698 0.10473600029945374 0.09820479974150656 0.09820479974150656 0.004061668684999473 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
63 0.0 0.0 0.0 0.0 0.0 0.014303999952971935 0.04790399968624115 0.020179199893027543 0.016447999514639378 0.009635010283506967 0.0 0.0 0.0 0.0 0.0 0.6221439838409424 0.6444799900054932 0.6277984082698822 0.6277984082698822 0.007234140179397069 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 8 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
64 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.03276799991726875 0.01921279989182949 0.015232000034302473 0.0065506148511265076 0.0 0.0 0.0 0.0 0.0 0.9111359715461731 0.9307839870452881 0.9151648044586183 0.9151648044586183 0.005528712062927265 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 16 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
65 0.0 0.0 0.0 0.0 0.0 0.014175999909639359 0.02707199938595295 0.016512000095099212 0.014688000082969666 0.0038989080209321414 0.0 0.0 0.0 0.0 0.0 1.7645119428634644 1.7849279642105103 1.7684095859527589 1.7684095859527589 0.005876963340184193 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 32 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
66 0.0 0.0 0.0 0.0 0.0 0.014240000396966934 0.029184000566601753 0.016825600154697896 0.014752000104635954 0.00457910514148248 0.0 0.0 0.0 0.0 0.0 3.4781761169433594 3.5388801097869873 3.490892815589905 3.490892815589905 0.01818910600692522 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 64 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
67 0.0 0.0 0.0 0.0 0.0 0.014976000413298607 0.03139200061559677 0.01898880014196038 0.016848000697791576 0.005083715524393418 0.13752702814163098 0.14117629917511842 0.13848196486571557 0.13848196486571557 0.0009880564964713527 0.523336967410432 0.5372236808930884 0.5269708253945994 0.5269708253945994 0.00375988994658546 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 520 False 512 BF16 generic none CUDA_EVENT True [512] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 8 8 9 8 16384.0 0.1111111111111111 q512_8q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
68 0.0 0.0 0.0 0.0 0.0 0.01833599992096424 0.02707199938595295 0.020995199866592883 0.01976000051945448 0.0028392656352050185 0.17817885890237703 0.18622915300900206 0.18109068484526028 0.18109068484526028 0.0027040006080457624 0.5449571488834201 0.5695788427872015 0.5538629212834322 0.5538629212834322 0.008270141985514729 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 1040 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 16 16 17 16 16384.0 0.058823529411764705 q1k_16q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
69 0.0 0.0 0.0 0.0 0.0 0.02703999914228916 0.03308799862861633 0.028883199393749236 0.02759999968111515 0.002285758578932753 0.4688266550410815 0.48301665772804186 0.4727750380198454 0.4727750380198454 0.004396396389258256 1.0430453981052807 1.0746153117238624 1.051829759343436 1.051829759343436 0.009781101336187197 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 32 32 33 32 16384.0 0.030303030303030304 q2k_32q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
70 0.0 0.0 0.0 0.0 0.0 0.04368000105023384 0.059328000992536545 0.04809600040316582 0.04617599956691265 0.005158792915002645 1.3509461459747514 1.3759066409666496 1.3589365122072 1.3589365122072 0.008008877716183384 0.9213738861449998 0.9383974724214122 0.9268234851606594 0.9268234851606594 0.005462224239661061 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 16 16 17 16 32768.0 0.058823529411764705 q4k_16q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
71 0.0 0.0 0.0 0.0 0.0 0.026944000273942947 0.040511999279260635 0.030291200056672095 0.02817599941045046 0.004386386489305873 0.5071830964059985 0.5142792136001758 0.5096392092471257 0.5096392092471257 0.0022059272685869546 2.175632932188972 2.2060727208328075 2.186168772243963 2.186168772243963 0.009462633998570079 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 32 32 33 32 32768.0 0.030303030303030304 q2k_32q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
72 0.0 0.0 0.0 0.0 0.0 0.018303999677300453 0.03017600066959858 0.02039040010422468 0.018943999893963337 0.0034612051983613614 0.21341429693945616 0.21552776300295579 0.21393496609766816 0.21393496609766816 0.0005736773262009222 4.617401495144284 4.663128147488988 4.628666619290515 4.628666619290515 0.012412001359412127 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 64 64 65 64 32768.0 0.015384615384615385 q1k_64q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
73 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.02364799939095974 0.01809599995613098 0.016352000646293163 0.0035481127058959038 0.04822399839758873 0.08566399663686752 0.05961279980838299 0.05961279980838299 0.011445665413968877 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 64 0.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 False 0.0 64.0 64 BF16 generic none CUDA_EVENT False q64 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
74 0.0 0.0 0.0 0.0 0.0 0.014175999909639359 0.020864000543951988 0.01668160008266568 0.015664000064134598 0.0025769063833097584 0.049695998430252075 0.08057600259780884 0.05882879942655563 0.05882879942655563 0.009515126108519331 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 128 0.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 False 0.0 128.0 128 BF16 generic none CUDA_EVENT False q128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
75 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.028704000636935234 0.017430400010198355 0.015056000091135502 0.004349294613335555 0.049855999648571014 0.07366400212049484 0.05459520071744919 0.05459520071744919 0.0069610920757925574 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 256 0.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 False 0.0 256.0 256 BF16 generic none CUDA_EVENT False q256 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
76 0.0 0.0 0.0 0.0 0.0 0.014336000196635723 0.03161599859595299 0.017788799852132796 0.015711999963968992 0.005005385723318659 0.06102399900555611 0.08179199695587158 0.06650560013949873 0.06650560013949873 0.006947995595801105 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 512 0.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 False 0.0 512.0 512 BF16 generic none CUDA_EVENT False q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
77 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.04416000097990036 0.019200000166893005 0.015488000120967627 0.008561241323364038 0.08054400235414505 0.09196799993515015 0.08607039973139763 0.08607039973139763 0.004145329035483754 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False q1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
78 0.0 0.0 0.0 0.0 0.0 0.017855999991297722 0.023391999304294586 0.019667199812829494 0.018463999964296818 0.0022577669687832585 0.18729600310325623 0.20585599541664124 0.19546559900045393 0.19546559900045393 0.006339068824303663 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
79 0.0 0.0 0.0 0.0 0.0 0.026240000501275063 0.03446400165557861 0.028297600522637367 0.027088000439107418 0.0025148441522922374 0.5754240155220032 0.5889919996261597 0.5800191938877105 0.5800191938877105 0.003858869273829596 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False q4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
80 0.0 0.0 0.0 0.0 0.0 0.04182400181889534 0.047200001776218414 0.043036799877882004 0.0423360001295805 0.0017073405772076728 2.063199996948242 2.0787200927734375 2.067151999473572 2.067151999473572 0.004959651271127835 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False q8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
81 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.05648000165820122 0.02270399993285537 0.017935999669134617 0.012377915150727689 0.049536000937223434 0.07196799665689468 0.056015999615192415 0.056015999615192415 0.0070476637552742884 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 64 448.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 True 448.0 512.0 64 BF16 generic none CUDA_EVENT False q64s512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
82 0.0 0.0 0.0 0.0 0.0 0.01408000010997057 0.021344000473618507 0.01611520005390048 0.014928000047802925 0.0025499884993961702 0.07072000205516815 0.2642880082130432 0.1588256008923054 0.1588256008923054 0.053220347086102376 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 128 896.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 True 896.0 1024.0 128 BF16 generic none CUDA_EVENT False q128s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
83 0.0 0.0 0.0 0.0 0.0 0.01360000018030405 0.03014400042593479 0.016975999902933837 0.015056000091135502 0.004715159697364111 0.08393599838018417 0.11036799848079681 0.09160000011324881 0.09160000011324881 0.007911669434472792 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 256 1792.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 True 1792.0 2048.0 256 BF16 generic none CUDA_EVENT False q256s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
84 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.020767999812960625 0.016233599931001663 0.015392000321298838 0.002202615907995427 0.1998399943113327 0.22070400416851044 0.20855360180139543 0.20855360180139543 0.00689307200230667 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 512 3584.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 3584.0 4096.0 512 BF16 generic none CUDA_EVENT False q512s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
85 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.033440001308918 0.018684800155460833 0.016048000194132328 0.00553991005639174 0.6043199896812439 0.635807991027832 0.6126143991947173 0.6126143991947173 0.008745933953408096 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 1024 7168.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 True 7168.0 8192.0 1024 BF16 generic none CUDA_EVENT False q1ks8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
86 0.0 0.0 0.0 0.0 0.0 0.013824000023305416 0.03359999880194664 0.017811199743300678 0.014944000169634819 0.005926140483565472 0.0 0.0 0.0 0.0 0.0 0.045471999794244766 0.07539200037717819 0.054758400097489356 0.054758400097489356 0.010253548506101549 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
87 0.0 0.0 0.0 0.0 0.0 0.014047999866306782 0.02409599907696247 0.01641279999166727 0.01473599998280406 0.003347158638713987 0.0 0.0 0.0 0.0 0.0 0.0461760014295578 0.07529599964618683 0.05460800044238568 0.05460800044238568 0.009748937798340135 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
88 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.028416000306606293 0.018611199874430894 0.01598400017246604 0.005209875093863647 0.0 0.0 0.0 0.0 0.0 0.048128001391887665 0.07897599786520004 0.061353600397706036 0.061353600397706036 0.010488153655157845 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
89 0.0 0.0 0.0 0.0 0.0 0.014112000353634357 0.025728000327944756 0.016092800162732603 0.01512000011280179 0.003300888123052605 0.0 0.0 0.0 0.0 0.0 0.04864000156521797 0.07648000121116638 0.05810560062527656 0.05810560062527656 0.009473544218404408 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
90 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.03551999852061272 0.018588799890130757 0.016064000315964222 0.006071057437992447 0.0 0.0 0.0 0.0 0.0 0.04822399839758873 0.07862400263547897 0.05660480037331582 0.05660480037331582 0.009565394213730401 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
91 0.0 0.0 0.0 0.0 0.0 0.014303999952971935 0.028831999748945236 0.01699519995599985 0.015024000313133001 0.004285000744868188 0.0 0.0 0.0 0.0 0.0 0.04854400083422661 0.06719999760389328 0.05778240002691746 0.05778240002691746 0.006852125554679805 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
92 0.0 0.0 0.0 0.0 0.0 0.0144640002399683 0.024927999824285507 0.0161183999851346 0.01521599991247058 0.0029774808524673907 0.0 0.0 0.0 0.0 0.0 0.05379199981689453 0.08966399729251862 0.06270079985260964 0.06270079985260964 0.009983591277092696 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
93 0.0 0.0 0.0 0.0 0.0 0.014431999996304512 0.03001599945127964 0.017648000083863736 0.01547200046479702 0.004585126309484848 0.0 0.0 0.0 0.0 0.0 0.061664000153541565 0.07692799717187881 0.06704320013523103 0.06704320013523103 0.005500191798490629 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
94 0.0 0.0 0.0 0.0 0.0 0.014175999909639359 0.026367999613285065 0.016947199776768684 0.015039999969303608 0.0037951566103550205 0.0 0.0 0.0 0.0 0.0 0.08799999952316284 0.111455999314785 0.0964031994342804 0.0964031994342804 0.007397541615558088 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
95 0.0 0.0 0.0 0.0 0.0 0.01369599997997284 0.021247999742627144 0.015359999984502793 0.014640000183135271 0.0020942770950814317 0.0 0.0 0.0 0.0 0.0 0.051711998879909515 0.07065600156784058 0.058054400235414506 0.058054400235414506 0.006633034815910025 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
96 0.0 0.0 0.0 0.0 0.0 0.014208000153303146 0.0307839997112751 0.017148799914866685 0.015039999969303608 0.004882374686312284 0.0 0.0 0.0 0.0 0.0 0.061919998377561576 0.07843200117349625 0.06628479920327664 0.06628479920327664 0.004962852689801192 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
97 0.0 0.0 0.0 0.0 0.0 0.013887999579310417 0.02969600073993206 0.017500799987465142 0.015232000034302473 0.00467273319705314 0.0 0.0 0.0 0.0 0.0 0.08819200098514557 0.11097600311040878 0.09493440166115762 0.09493440166115762 0.007509235042985577 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
98 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.022112000733613968 0.01751680001616478 0.016047999262809753 0.0030306621792915785 0.0 0.0 0.0 0.0 0.0 0.13065600395202637 0.15110400319099426 0.13857279866933822 0.13857279866933822 0.00750137841249771 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
99 0.0 0.0 0.0 0.0 0.0 0.013919999822974205 0.04012800008058548 0.01892479993402958 0.01550400024279952 0.007459545267816961 0.0 0.0 0.0 0.0 0.0 0.06278400123119354 0.08259200304746628 0.0704512007534504 0.0704512007534504 0.005979055984382744 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
100 0.0 0.0 0.0 0.0 0.0 0.014336000196635723 0.02236800082027912 0.016332800220698118 0.014928000047802925 0.002784044363186731 0.0 0.0 0.0 0.0 0.0 0.1003199964761734 0.1279360055923462 0.10921279862523078 0.10921279862523078 0.00862769617046716 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
101 0.0 0.0 0.0 0.0 0.0 0.013919999822974205 0.0225600004196167 0.016128000058233737 0.014800000004470348 0.002958953332547708 0.0 0.0 0.0 0.0 0.0 0.13116799294948578 0.14812800288200378 0.13783999979496003 0.13783999979496003 0.005696384361148053 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
102 0.0 0.0 0.0 0.0 0.0 0.014208000153303146 0.029983999207615852 0.017468800116330386 0.01508800033479929 0.0047379550962483065 0.0 0.0 0.0 0.0 0.0 0.217631995677948 0.2447360008955002 0.22715839892625808 0.22715839892625808 0.008831828221847138 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
103 0.0 0.0 0.0 0.0 0.0 0.014047999866306782 0.02304000034928322 0.016512000095099212 0.014512000139802694 0.0035026774828624254 0.0 0.0 0.0 0.0 0.0 0.11020799726247787 0.12307199835777283 0.11600959971547126 0.11600959971547126 0.004667637266950902 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
104 0.0 0.0 0.0 0.0 0.0 0.014112000353634357 0.042080000042915344 0.017510399967432023 0.014607999939471483 0.00823117883530167 0.0 0.0 0.0 0.0 0.0 0.15702399611473083 0.17587199807167053 0.16399359852075576 0.16399359852075576 0.006588299074676393 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
105 0.0 0.0 0.0 0.0 0.0 0.013919999822974205 0.0208320003002882 0.015299199987202883 0.01462399959564209 0.001916768086505386 0.0 0.0 0.0 0.0 0.0 0.21779200434684753 0.2415360063314438 0.2260768011212349 0.2260768011212349 0.007251352080685236 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
106 0.0 0.0 0.0 0.0 0.0 0.014015999622642994 0.021088000386953354 0.015619200188666582 0.01473599998280406 0.002013227452302141 0.0 0.0 0.0 0.0 0.0 0.3959999978542328 0.4152640104293823 0.40332479774951924 0.40332479774951924 0.006942401431914052 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
107 0.0 0.0 0.0 0.0 0.0 0.014175999909639359 0.03379200026392937 0.020595200080424547 0.019600000232458115 0.006548754248881344 0.026192623739694512 0.040006882507168426 0.029155180178492036 0.029155180178492036 0.00408828748438241 0.024591375524545756 0.037561119537986146 0.027372820355088746 0.027372820355088746 0.0038383559348575944 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 72 False 64 BF16 generic none CUDA_EVENT True [64] [0] [512, 512, 512, 512, 512, 512, 512, 512] 1 8 8 9 8 512.0 0.1111111111111111 q64_8q1s512 fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
108 0.0 0.0 0.0 0.0 0.0 0.013856000266969204 0.020896000787615776 0.015318400040268899 0.014431999996304512 0.0019640312960926966 0.029349018208693862 0.06236262941356679 0.03714313592014963 0.03714313592014963 0.009618313791872569 0.028826981462526914 0.06125337308649041 0.036482463672774496 0.036482463672774496 0.009447230957011863 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 136 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 8 8 9 8 1024.0 0.1111111111111111 q128_8q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
109 0.0 0.0 0.0 0.0 0.0 0.013856000266969204 0.032127998769283295 0.017286399938166143 0.014479999896138906 0.005536495446636193 0.03273085874558354 0.04394578491937082 0.03563837490653034 0.03563837490653034 0.003429601730256567 0.03488514202593899 0.04683821345079978 0.037984025407085474 0.037984025407085474 0.0036553316361902684 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 144 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 16 16 17 16 1024.0 0.058823529411764705 q128_16q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
110 0.0 0.0 0.0 0.0 0.0 0.013856000266969204 0.021503999829292297 0.015078400075435639 0.01425600005313754 0.002238435975478849 0.042100813549974185 0.051784144690147756 0.045378692890289625 0.045378692890289625 0.003184109940650555 0.05111518843748309 0.06287185663927425 0.05509490773570219 0.05509490773570219 0.0038658725544299132 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 272 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 16 16 17 16 2048.0 0.058823529411764705 q256_16q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
111 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.02687999978661537 0.017667199857532977 0.01566399959847331 0.003864811846387173 0.048475323773821306 0.05599956978723733 0.05123499252968345 0.05123499252968345 0.002427379820423941 0.08429268135885387 0.09737642835214408 0.0890914090616175 0.0890914090616175 0.0042209177332077005 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 288 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 32 32 33 32 2048.0 0.030303030303030304 q256_32q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
112 0.0 0.0 0.0 0.0 0.0 0.01462399959564209 0.03359999880194664 0.019804799742996693 0.016032000072300434 0.006750519908145474 0.07121508474579985 0.07292308367136396 0.07194410845270183 0.07194410845270183 0.0005500065915943844 0.14760091249712767 0.15114092373010238 0.14911189243564577 0.14911189243564577 0.0011399477384397005 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 544 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q512_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
113 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.021856000646948814 0.016835200227797033 0.015263999812304974 0.00283854448975065 0.08146338272142935 0.08560865714384096 0.0834932625520734 0.0834932625520734 0.0012259635905347874 0.2782486219401307 0.29240733788179385 0.2851819365989658 0.2851819365989658 0.004187435731481665 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 576 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 64 64 65 64 4096.0 0.015384615384615385 q512_64q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
114 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.04495999962091446 0.02143679987639189 0.015856000129133463 0.009709987872683342 0.1194459208702178 0.12302524755181463 0.12053885718696096 0.12053885718696096 0.001005118119341339 0.5597220650459199 0.5764947443228802 0.5648435507167102 0.5648435507167102 0.004709970715400788 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192] 1 64 64 65 64 8192.0 0.015384615384615385 q1k_64q1s8k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
115 0.0 0.0 0.0 0.0 0.0 0.018112000077962875 0.026496000587940216 0.019318400137126445 0.018432000651955605 0.0024249605112359905 0.19770253574610402 0.222811797868348 0.2054811520619412 0.2054811520619412 0.008000944254868043 0.13941746080159492 0.157124211777114 0.14490284788179197 0.14490284788179197 0.005642170080515992 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q2k_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
116 0.0 0.0 0.0 0.0 0.0 0.02595200017094612 0.03155200183391571 0.02727359998971224 0.026575999334454536 0.0016260948764843166 0.6014684881116659 0.6095472988212 0.6046757700946376 0.6046757700946376 0.0023537435563177303 0.11325152264578045 0.11477269562841545 0.11385542721485654 0.11385542721485654 0.0004431903698023628 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 16 16 17 16 4096.0 0.058823529411764705 q4k_16q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
117 0.0 0.0 0.0 0.0 0.0 0.014303999952971935 0.03359999880194664 0.01814719969406724 0.015375999733805656 0.005678506740662529 0.06774400174617767 0.07891199737787247 0.07312640026211739 0.07312640026211739 0.003826583051422731 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 2 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512] 1024 512 512 512.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False 2q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
118 0.0 0.0 0.0 0.0 0.0 0.01788800023496151 0.028543999418616295 0.021340799890458582 0.019504000432789326 0.003718627037219618 0.09548799693584442 0.1327359974384308 0.10823359936475753 0.10823359936475753 0.013230635292043864 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 4 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512] 2048 512 512 512.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False 4q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
119 0.0 0.0 0.0 0.0 0.0 0.02627200074493885 0.030368000268936157 0.027184000052511693 0.02643200010061264 0.0013545679205210022 0.14364799857139587 0.1597760021686554 0.15008639842271806 0.15008639842271806 0.005367723415171222 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512] 4096 512 512 512.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 8q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
120 0.0 0.0 0.0 0.0 0.0 0.04150399938225746 0.04726399853825569 0.042950399965047834 0.04224000126123428 0.001720147501765378 0.2433920055627823 0.28963199257850647 0.2549152016639709 0.2549152016639709 0.013450991019687407 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512] 8192 512 512 512.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 16q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
121 0.0 0.0 0.0 0.0 0.0 0.025887999683618546 0.03407999873161316 0.028303999826312064 0.026367999613285065 0.0028877495368841042 0.325439989566803 0.3441599905490875 0.33442879617214205 0.33442879617214205 0.005693597811441922 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 2 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048] 4096 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 2q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
122 0.0 0.0 0.0 0.0 0.0 0.04137599840760231 0.05084799975156784 0.044828799366950986 0.043087998405098915 0.003560363865797613 0.6110399961471558 0.6421759724617004 0.6204223990440368 0.6204223990440368 0.011214490370794758 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 4 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048, 2048, 2048] 8192 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 4q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
123 0.0 0.0 0.0 0.0 0.0 0.014816000126302242 0.02364799939095974 0.016668799985200166 0.01592000015079975 0.0025515238179941247 0.0 0.0 0.0 0.0 0.0 0.0544000007212162 0.09014400094747543 0.06511679962277411 0.06511679962277411 0.013005726711295521 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
124 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.0208320003002882 0.016604799963533878 0.01566399959847331 0.0021353594266203244 0.0 0.0 0.0 0.0 0.0 0.17871999740600586 0.1961279958486557 0.18568639904260634 0.18568639904260634 0.004566142885274747 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
125 0.0 0.0 0.0 0.0 0.0 0.014431999996304512 0.02006400004029274 0.015619200002402068 0.01508800033479929 0.001572984783715635 0.0 0.0 0.0 0.0 0.0 0.2730880081653595 0.29721599817276 0.2815328001976013 0.2815328001976013 0.007016534727616923 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
126 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.02755199931561947 0.018678399827331306 0.015919999685138464 0.004323555372382858 0.0 0.0 0.0 0.0 0.0 0.3893119990825653 0.44041600823402405 0.40225600004196166 0.40225600004196166 0.013442998165884852 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
127 0.0 0.0 0.0 0.0 0.0 0.014303999952971935 0.02659199945628643 0.016748800035566093 0.015343999955803156 0.0036412341868394082 0.0 0.0 0.0 0.0 0.0 0.7404800057411194 0.9689919948577881 0.8451807916164398 0.8451807916164398 0.08637455920036795 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
128 0.0 0.0 0.0 0.0 0.0 0.014751999638974667 0.02160000056028366 0.016752000153064727 0.01521599991247058 0.0025167650350367246 0.0 0.0 0.0 0.0 0.0 0.06412799656391144 0.08956799656152725 0.07242240011692047 0.07242240011692047 0.009797120588901621 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
129 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.022911999374628067 0.016137600038200618 0.015343999955803156 0.002330911555470513 0.0 0.0 0.0 0.0 0.0 0.3128319978713989 0.3282879889011383 0.3203647971153259 0.3203647971153259 0.004598568238907996 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
130 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.03574400022625923 0.01919359974563122 0.01583999954164028 0.006642521913489215 0.0 0.0 0.0 0.0 0.0 0.5050879716873169 0.5311999917030334 0.511932796239853 0.511932796239853 0.007150929647317677 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
131 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.02595200017094612 0.016992000117897987 0.015456000342965126 0.003390731937723684 0.0 0.0 0.0 0.0 0.0 0.7385600209236145 0.7681919932365417 0.7483008027076722 0.7483008027076722 0.010214373356208012 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
132 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.038975998759269714 0.01952639976516366 0.015327999833971262 0.007695927285621061 0.0 0.0 0.0 0.0 0.0 1.4228800535202026 1.5237760543823242 1.4435008168220522 1.4435008168220522 0.0342955291725742 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
133 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.03907199949026108 0.01793599994853139 0.015248000156134367 0.007167103363234667 0.0 0.0 0.0 0.0 0.0 0.06947200000286102 0.08857599645853043 0.07469440028071403 0.07469440028071403 0.00583249952929747 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
134 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.02175999991595745 0.016710399929434062 0.015327999833971262 0.002705383977079183 0.0 0.0 0.0 0.0 0.0 0.388480007648468 0.4073280096054077 0.3966591984033584 0.3966591984033584 0.004487315516095964 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 8 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
135 0.0 0.0 0.0 0.0 0.0 0.0144640002399683 0.022048000246286392 0.017011200170964004 0.015392000321298838 0.002776899649845722 0.0 0.0 0.0 0.0 0.0 0.622048020362854 0.6347839832305908 0.6262047946453094 0.6262047946453094 0.004593360122958751 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 16 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
136 0.0 0.0 0.0 0.0 0.0 0.014592000283300877 0.02937600016593933 0.01847040019929409 0.015344000421464443 0.005043809142122341 0.0 0.0 0.0 0.0 0.0 0.9105280041694641 0.9304640293121338 0.914108806848526 0.914108806848526 0.00563919268816644 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 32 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
137 0.0 0.0 0.0 0.0 0.0 0.01462399959564209 0.039903998374938965 0.01791359977796674 0.015440000221133232 0.007367547649297217 0.0 0.0 0.0 0.0 0.0 1.764799952507019 1.7965760231018066 1.770739197731018 1.770739197731018 0.009082122770320404 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 64 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
138 0.0 0.0 0.0 0.0 0.0 0.015168000012636185 0.03187200054526329 0.018553599901497363 0.016127999871969223 0.0050628774268006264 0.16963527081512533 0.1737871320906266 0.17088926838108623 0.17088926838108623 0.0011703114258121128 0.47362872483230506 0.48522089403242025 0.47712993814280913 0.47712993814280913 0.0032675581298664976 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 520 False 512 BF16 generic none CUDA_EVENT True [512] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 8 8 9 8 16384.0 0.1111111111111111 q512_8q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
139 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.03868800029158592 0.01921919994056225 0.016959999687969685 0.006691309533030663 0.1589600576212269 0.16117782913137854 0.15969057520605917 0.15969057520605917 0.0006212984448748182 0.5199519263456005 0.5272061673552852 0.5223414198520004 0.5223414198520004 0.002032242112153396 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 1040 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 16 16 17 16 16384.0 0.058823529411764705 q1k_16q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
140 0.0 0.0 0.0 0.0 0.0 0.018400000408291817 0.024320000782608986 0.019910399988293647 0.0191040001809597 0.001841532763984352 0.25650752966102763 0.27066608538463055 0.259736894547936 0.259736894547936 0.00462927315947332 0.5278764825612624 0.5570139063374764 0.5345223138928448 0.5345223138928448 0.009526755161797178 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 32 32 33 32 16384.0 0.030303030303030304 q2k_32q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
141 0.0 0.0 0.0 0.0 0.0 0.026048000901937485 0.03728000074625015 0.028636799938976765 0.02705600019544363 0.003313953649011259 0.9270006318443208 0.9712965120641314 0.93480767601568 0.93480767601568 0.012612551450284608 0.8181833128578277 0.8572794566782395 0.8250739157811953 0.8250739157811953 0.01113200873299586 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 16 16 17 16 32768.0 0.058823529411764705 q4k_16q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
142 0.0 0.0 0.0 0.0 0.0 0.018079999834299088 0.037696000188589096 0.022092800214886667 0.019024000503122807 0.005986278786633071 0.2839857165542317 0.2876110048757805 0.2849506939696605 0.2849506939696605 0.0009995178425916847 1.0871823008331585 1.101060989333509 1.0908765231323903 1.0908765231323903 0.0038264533900426207 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 32 32 33 32 32768.0 0.030303030303030304 q2k_32q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
143 0.0 0.0 0.0 0.0 0.0 0.015072000212967396 0.025567999109625816 0.01726400014013052 0.015728000551462173 0.0031324465940990903 0.137270464802061 0.13799613818579368 0.13751499486424038 0.13751499486424038 0.00025221761530472904 2.3021855212208884 2.314355908780759 2.3062865750744197 2.3062865750744197 0.004229983070201486 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 64 64 65 64 32768.0 0.015384615384615385 q1k_64q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
144 0.0 0.0 0.0 0.0 0.0 0.014560000039637089 0.022784000262618065 0.016435200069099664 0.015519999898970127 0.0023688301421469523 0.04879999905824661 0.09139200299978256 0.06054079942405224 0.06054079942405224 0.012152608702448775 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 64 0.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 False 0.0 64.0 64 BF16 generic none CUDA_EVENT False q64 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
145 0.0 0.0 0.0 0.0 0.0 0.014816000126302242 0.02844800055027008 0.017008000146597625 0.015696000307798386 0.003941466294662679 0.047807998955249786 0.07356800138950348 0.05626560002565384 0.05626560002565384 0.00842179125412236 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 128 0.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 False 0.0 128.0 128 BF16 generic none CUDA_EVENT False q128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
146 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.053408000618219376 0.019353600218892097 0.01532800029963255 0.01138302400841626 0.048448000103235245 0.0785600021481514 0.0556256003677845 0.0556256003677845 0.009348274502616908 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 256 0.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 False 0.0 256.0 256 BF16 generic none CUDA_EVENT False q256 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
147 0.0 0.0 0.0 0.0 0.0 0.015039999969303608 0.03139200061559677 0.01823679991066456 0.016159999649971724 0.004860071238302512 0.055424001067876816 0.08505599945783615 0.0640383992344141 0.0640383992344141 0.00921448636178623 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 512 0.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 False 0.0 512.0 512 BF16 generic none CUDA_EVENT False q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
148 0.0 0.0 0.0 0.0 0.0 0.014751999638974667 0.026528000831604004 0.017324799951165915 0.01536000007763505 0.0036004822686428305 0.07660800218582153 0.0942080020904541 0.08209280073642732 0.08209280073642732 0.00515895587669752 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False q1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
149 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.021247999742627144 0.016403199825435876 0.01532800029963255 0.001995897022647934 0.11395200341939926 0.15113599598407745 0.12431039959192276 0.12431039959192276 0.011164431123683732 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
150 0.0 0.0 0.0 0.0 0.0 0.017184000462293625 0.028672000393271446 0.019865600019693376 0.017823999747633934 0.0035798491315929977 0.3171840012073517 0.3341119885444641 0.3261695951223373 0.3261695951223373 0.005111046452878918 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False q4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
151 0.0 0.0 0.0 0.0 0.0 0.024639999493956566 0.030400000512599945 0.02656640000641346 0.02556800004094839 0.0020189846603237303 1.0648640394210815 1.0828479528427124 1.0715327858924866 1.0715327858924866 0.005558639263049851 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False q8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
152 0.0 0.0 0.0 0.0 0.0 0.014976000413298607 0.021695999428629875 0.017305599898099898 0.01593599934130907 0.0025718046517268054 0.04956800118088722 0.07932800054550171 0.06228480041027069 0.06228480041027069 0.01027160349757827 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 64 448.0 True FLASH_ATTN False vllm020_batch_spec [64] 64 64 64 64.0 True 0.0 0.0 0.0 True 448.0 512.0 64 BF16 generic none CUDA_EVENT False q64s512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
153 0.0 0.0 0.0 0.0 0.0 0.01539199985563755 0.03580800071358681 0.019686400331556796 0.017136000096797943 0.005918387811304003 0.05158400163054466 0.10713600367307663 0.06364160068333148 0.06364160068333148 0.015832957809696766 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 128 896.0 True FLASH_ATTN False vllm020_batch_spec [128] 128 128 128 128.0 True 0.0 0.0 0.0 True 896.0 1024.0 128 BF16 generic none CUDA_EVENT False q128s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
154 0.0 0.0 0.0 0.0 0.0 0.015168000012636185 0.02223999984562397 0.016672000009566545 0.015887999907135963 0.0020934945946034563 0.06521599739789963 0.08902399986982346 0.07520959973335266 0.07520959973335266 0.007913840684102929 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 256 1792.0 True FLASH_ATTN False vllm020_batch_spec [256] 256 256 256 256.0 True 0.0 0.0 0.0 True 1792.0 2048.0 256 BF16 generic none CUDA_EVENT False q256s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
155 0.0 0.0 0.0 0.0 0.0 0.015231999568641186 0.04028800129890442 0.019971200078725816 0.01646399963647127 0.007351305886577286 0.14467200636863708 0.16844800114631653 0.15363519936800005 0.15363519936800005 0.008174435899956223 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 512 3584.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 3584.0 4096.0 512 BF16 generic none CUDA_EVENT False q512s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
156 0.0 0.0 0.0 0.0 0.0 0.015519999898970127 0.02304000034928322 0.01775679988786578 0.016784000210464 0.0025077243712082584 0.33740800619125366 0.35343998670578003 0.3445120006799698 0.3445120006799698 0.00445648463590358 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 1024 7168.0 True FLASH_ATTN False vllm020_batch_spec [1024] 1024 1024 1024 1024.0 True 0.0 0.0 0.0 True 7168.0 8192.0 1024 BF16 generic none CUDA_EVENT False q1ks8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
157 0.0 0.0 0.0 0.0 0.0 0.015647999942302704 0.02393599972128868 0.01809599995613098 0.01654400024563074 0.002998393102466254 0.0 0.0 0.0 0.0 0.0 0.0504320003092289 0.0843840017914772 0.060083200410008426 0.060083200410008426 0.00986959318572296 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
158 0.0 0.0 0.0 0.0 0.0 0.01603199914097786 0.030047999694943428 0.019510399922728537 0.017680000513792038 0.004065185265963332 0.0 0.0 0.0 0.0 0.0 0.05004800111055374 0.07036799937486649 0.059315200522542 0.059315200522542 0.006537768821329647 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
159 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.02393599972128868 0.018035199772566558 0.016512000001966953 0.0030667689116777724 0.0 0.0 0.0 0.0 0.0 0.05100800096988678 0.06735999882221222 0.058387200161814694 0.058387200161814694 0.005832787739241381 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
160 0.0 0.0 0.0 0.0 0.0 0.01500799972563982 0.026208000257611275 0.017500799987465142 0.01646399963647127 0.0030666103306165714 0.0 0.0 0.0 0.0 0.0 0.05023999884724617 0.07254400104284286 0.057254400476813315 0.057254400476813315 0.006890853653068151 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
161 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.027327999472618103 0.0179776000790298 0.01648000068962574 0.003783417447531392 0.0 0.0 0.0 0.0 0.0 0.04819199815392494 0.07100799679756165 0.05621119923889638 0.05621119923889638 0.007824391484124725 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 128.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s128 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
162 0.0 0.0 0.0 0.0 0.0 0.015647999942302704 0.036448001861572266 0.019136000238358975 0.016704000532627106 0.006076530095624803 0.0 0.0 0.0 0.0 0.0 0.047488000243902206 0.08441600203514099 0.0588383998721838 0.0588383998721838 0.011275940726332522 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
163 0.0 0.0 0.0 0.0 0.0 0.015135999768972397 0.033952001482248306 0.02119360016658902 0.018000000156462193 0.007136646614305304 0.0 0.0 0.0 0.0 0.0 0.04931199923157692 0.06992000341415405 0.05755840018391609 0.05755840018391609 0.007297587694315226 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
164 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.034272000193595886 0.0204415999352932 0.017311999574303627 0.00695404701803013 0.0 0.0 0.0 0.0 0.0 0.05215999856591225 0.0735040009021759 0.06117440015077591 0.06117440015077591 0.007381118436894922 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
165 0.0 0.0 0.0 0.0 0.0 0.015359999611973763 0.03743999823927879 0.02012479966506362 0.01775999926030636 0.006181045509079057 0.0 0.0 0.0 0.0 0.0 0.06355199962854385 0.08508799970149994 0.07019200026988984 0.07019200026988984 0.0062246580442117845 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 1024.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s1k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
166 0.0 0.0 0.0 0.0 0.0 0.015552000142633915 0.032607998698949814 0.01959999995306134 0.017487999983131886 0.004882475068460749 0.0 0.0 0.0 0.0 0.0 0.04918399825692177 0.0865280032157898 0.05973760038614274 0.05973760038614274 0.011546847942113974 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
167 0.0 0.0 0.0 0.0 0.0 0.015168000012636185 0.02675200067460537 0.017430400010198355 0.016560000367462635 0.003243135094239819 0.0 0.0 0.0 0.0 0.0 0.052671998739242554 0.08367999643087387 0.06238719932734965 0.06238719932734965 0.011207824780630104 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
168 0.0 0.0 0.0 0.0 0.0 0.01500799972563982 0.03612799942493439 0.019327999837696553 0.01688000001013279 0.006058251425153085 0.0 0.0 0.0 0.0 0.0 0.06364800035953522 0.07878399640321732 0.06935679838061332 0.06935679838061332 0.004515588328677643 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
169 0.0 0.0 0.0 0.0 0.0 0.015104000456631184 0.03711999952793121 0.019670399930328132 0.017152000218629837 0.006165994646522264 0.0 0.0 0.0 0.0 0.0 0.09071999788284302 0.11507199704647064 0.10252480059862136 0.10252480059862136 0.008782544051535657 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 2048.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
170 0.0 0.0 0.0 0.0 0.0 0.015039999969303608 0.026528000831604004 0.018396800104528665 0.01601599995046854 0.004279788048986283 0.0 0.0 0.0 0.0 0.0 0.05331199988722801 0.07977599650621414 0.06076480001211167 0.06076480001211167 0.008761579122069606 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
171 0.0 0.0 0.0 0.0 0.0 0.015359999611973763 0.02643200010061264 0.01726400004699826 0.015855999663472176 0.003210008417242029 0.0 0.0 0.0 0.0 0.0 0.062431998550891876 0.08246400207281113 0.06970879957079888 0.06970879957079888 0.007016341676068233 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
172 0.0 0.0 0.0 0.0 0.0 0.014911999925971031 0.02223999984562397 0.0166015999391675 0.015887999907135963 0.00204913969129354 0.0 0.0 0.0 0.0 0.0 0.10127999633550644 0.1141119971871376 0.10621120035648347 0.10621120035648347 0.004029318311754605 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
173 0.0 0.0 0.0 0.0 0.0 0.015359999611973763 0.03363199904561043 0.019305599946528675 0.016671999357640743 0.0055445582307981234 0.0 0.0 0.0 0.0 0.0 0.1319040060043335 0.15839999914169312 0.14040640145540234 0.14040640145540234 0.007998041073596942 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 4096.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s4k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
174 0.0 0.0 0.0 0.0 0.0 0.014368000440299511 0.04447999969124794 0.018908800091594458 0.0157279996201396 0.0086814937461721 0.0 0.0 0.0 0.0 0.0 0.06428799778223038 0.08982399851083755 0.07349760085344315 0.07349760085344315 0.008605284512197258 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
175 0.0 0.0 0.0 0.0 0.0 0.015104000456631184 0.028672000393271446 0.01890560006722808 0.016080000437796116 0.004797584627815021 0.0 0.0 0.0 0.0 0.0 0.11123199760913849 0.14115199446678162 0.11942399889230729 0.11942399889230729 0.008513394706791027 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
176 0.0 0.0 0.0 0.0 0.0 0.014271999709308147 0.024927999824285507 0.016915200091898442 0.015216000378131866 0.003374147499442635 0.0 0.0 0.0 0.0 0.0 0.15887999534606934 0.18111999332904816 0.16934399753808976 0.16934399753808976 0.007415181260761123 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
177 0.0 0.0 0.0 0.0 0.0 0.014336000196635723 0.026944000273942947 0.017737600207328796 0.015199999790638685 0.00415598714375255 0.0 0.0 0.0 0.0 0.0 0.2192319929599762 0.23472000658512115 0.22809920012950893 0.22809920012950893 0.004730841376327335 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 8192.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s8k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
178 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.05052800104022026 0.020320000313222408 0.015520000364631414 0.010604522177924678 0.024270629882498958 0.03340247625954076 0.028446344104128624 0.028446344104128624 0.0032330369099793834 0.023697370291069768 0.03261352722995356 0.027774456325453972 0.027774456325453972 0.0031566742680923386 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 72 False 64 BF16 generic none CUDA_EVENT True [64] [0] [512, 512, 512, 512, 512, 512, 512, 512] 1 8 8 9 8 512.0 0.1111111111111111 q64_8q1s512 fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
179 0.0 0.0 0.0 0.0 0.0 0.015359999611973763 0.033663999289274216 0.019987199828028678 0.018240000121295452 0.005522929139253732 0.0259194055660947 0.03719755183990719 0.029916029687899703 0.029916029687899703 0.003966666590554318 0.027104595853449518 0.03889844644729374 0.03128396954022015 0.03128396954022015 0.004148046317967881 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 136 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 8 8 9 8 1024.0 0.1111111111111111 q128_8q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
180 0.0 0.0 0.0 0.0 0.0 0.014592000283300877 0.03299200162291527 0.019840000104159115 0.016207999549806118 0.006546343008726814 0.02587869595769926 0.03763167265431482 0.030174939058162802 0.030174939058162802 0.0037303581782277364 0.026473304070195713 0.03849632587654989 0.03086826083864964 0.03086826083864964 0.003816069654529222 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 144 False 128 BF16 generic none CUDA_EVENT True [128] [0] [1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024, 1024] 1 16 16 17 16 1024.0 0.058823529411764705 q128_16q1s1k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
181 0.0 0.0 0.0 0.0 0.0 0.013824000023305416 0.021023999899625778 0.016304000187665223 0.015584000386297703 0.0023236165806545476 0.031810621525966996 0.04156949936878106 0.0346749350032807 0.0346749350032807 0.003130209181143985 0.035677378270900374 0.04662250161636451 0.038889864871740294 0.038889864871740294 0.0035107033960828727 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 272 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 16 16 17 16 2048.0 0.058823529411764705 q256_16q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
182 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.02175999991595745 0.01569600012153387 0.015008000191301107 0.0020882666168036863 0.038211712107062853 0.07212229256520057 0.04364509673334097 0.04364509673334097 0.009671953074025085 0.0476442859917874 0.08992570455184198 0.05441890342616107 0.05441890342616107 0.01205947791784038 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 288 False 256 BF16 generic none CUDA_EVENT True [256] [0] [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] 1 32 32 33 32 2048.0 0.030303030303030304 q256_32q1s2k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
183 0.0 0.0 0.0 0.0 0.0 0.014368000440299511 0.033824000507593155 0.017628800217062236 0.014864000026136637 0.005791495403857738 0.05214261250030033 0.06266261508706669 0.05677791295527661 0.05677791295527661 0.0030298223079651514 0.08648138506878382 0.10392938682791132 0.09416928531647478 0.09416928531647478 0.005025126612204489 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 544 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q512_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
184 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.031199999153614044 0.017900799959897996 0.015343999955803156 0.004974475661316249 0.06411958891421111 0.07405276123263956 0.06793047918211377 0.06793047918211377 0.0033918658556700006 0.14058441263169497 0.16236323591492058 0.1489399211274489 0.1489399211274489 0.00743678300375353 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 576 False 512 BF16 generic none CUDA_EVENT True [512] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 64 64 65 64 4096.0 0.015384615384615385 q512_64q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
185 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.03855999931693077 0.018495999928563833 0.015647999942302704 0.006918530056761627 0.09872985549401277 0.10683454583043753 0.10185316839884552 0.10185316839884552 0.0020802254037042074 0.2743261390166379 0.2968454508984596 0.2830044295482752 0.2830044295482752 0.005780016596065092 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192] 1 64 64 65 64 8192.0 0.015384615384615385 q1k_64q1s8k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
186 0.0 0.0 0.0 0.0 0.0 0.014911999925971031 0.030400000512599945 0.01977920001372695 0.01726400014013052 0.005350883464206169 0.13918872472233365 0.16279522855335207 0.1501912864839173 0.1501912864839173 0.008992185529011513 0.11892328861766266 0.13909276049083735 0.1283239123428725 0.1283239123428725 0.007682951884956939 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 32 32 33 32 4096.0 0.030303030303030304 q2k_32q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
187 0.0 0.0 0.0 0.0 0.0 0.01727999933063984 0.02223999984562397 0.01819519978016615 0.017680000513792038 0.0014397298270620873 0.3728044181625443 0.38295504353701676 0.3761264483787333 0.3761264483787333 0.0033660272332490977 0.07967557017401883 0.08184495665371805 0.08038555277807365 0.08038555277807365 0.0007193856241088455 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096] 1 16 16 17 16 4096.0 0.058823529411764705 q4k_16q1s4k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
188 0.0 0.0 0.0 0.0 0.0 0.01500799972563982 0.034591998904943466 0.01941439984366298 0.01756799966096878 0.005541380584373771 0.05951999872922897 0.08268799632787704 0.06715519949793816 0.06715519949793816 0.006657802116288364 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 2 1024 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512] 1024 512 512 512.0 True 0.0 0.0 0.0 False 0.0 1024.0 1024 BF16 generic none CUDA_EVENT False 2q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
189 0.0 0.0 0.0 0.0 0.0 0.015104000456631184 0.03283200040459633 0.019180799927562477 0.016543999314308167 0.0052187911233635975 0.07199999690055847 0.08675199747085571 0.07749439924955369 0.07749439924955369 0.004849874741156772 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 4 2048 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512] 2048 512 512 512.0 True 0.0 0.0 0.0 False 0.0 2048.0 2048 BF16 generic none CUDA_EVENT False 4q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
190 0.0 0.0 0.0 0.0 0.0 0.01724799908697605 0.02284800074994564 0.01928640007972717 0.018400000408291817 0.0020641390157565697 0.09676799923181534 0.12310399860143663 0.10618879944086074 0.10618879944086074 0.008982738207839057 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512] 4096 512 512 512.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 8q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
191 0.0 0.0 0.0 0.0 0.0 0.024224000051617622 0.03315199911594391 0.027436799928545953 0.027328000403940678 0.002679154874546328 0.14716799557209015 0.16412800550460815 0.15470399856567385 0.15470399856567385 0.005423454433987419 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512] 8192 512 512 512.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 16q512 measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
192 0.0 0.0 0.0 0.0 0.0 0.01833599992096424 0.04806400090456009 0.026252799853682517 0.022672000341117382 0.00878438440429033 0.1844799965620041 0.2072959989309311 0.19359359890222552 0.19359359890222552 0.007663539820967659 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 2 4096 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048] 4096 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 4096.0 4096 BF16 generic none CUDA_EVENT False 2q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
193 0.0 0.0 0.0 0.0 0.0 0.024480000138282776 0.04979199916124344 0.029081599973142146 0.025679999962449074 0.007227422044689197 0.34147199988365173 0.37968000769615173 0.3583200007677078 0.3583200007677078 0.011804422100726231 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 4 8192 0.0 True FLASH_ATTN False vllm020_batch_spec [2048, 2048, 2048, 2048] 8192 2048 2048 2048.0 True 0.0 0.0 0.0 False 0.0 8192.0 8192 BF16 generic none CUDA_EVENT False 4q2k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
194 0.0 0.0 0.0 0.0 0.0 0.014720000326633453 0.023744000121951103 0.017753600236028434 0.016368000768125057 0.003061040281616705 0.0 0.0 0.0 0.0 0.0 0.05686400085687637 0.1090880036354065 0.06629760004580021 0.06629760004580021 0.014803727026812366 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
195 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.021088000386953354 0.01647359998896718 0.015840000472962856 0.0017964402433206 0.0 0.0 0.0 0.0 0.0 0.08540800213813782 0.09961599856615067 0.09146559983491898 0.09146559983491898 0.00447423706371901 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
196 0.0 0.0 0.0 0.0 0.0 0.014560000039637089 0.04156799986958504 0.018512000143527985 0.015584000386297703 0.007849701681877904 0.0 0.0 0.0 0.0 0.0 0.17948800325393677 0.194815993309021 0.1866239994764328 0.1866239994764328 0.004156328241374654 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
197 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.029632000252604485 0.019449600111693145 0.016736000776290894 0.005126811425136928 0.0 0.0 0.0 0.0 0.0 0.27529600262641907 0.2898879945278168 0.2825664013624191 0.2825664013624191 0.004542801609674093 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
198 0.0 0.0 0.0 0.0 0.0 0.014399999752640724 0.031328000128269196 0.019759999960660933 0.016367999836802483 0.006266303740589241 0.0 0.0 0.0 0.0 0.0 0.39190399646759033 0.4079039990901947 0.3987520009279252 0.3987520009279252 0.0037367727509362725 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 16384.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
199 0.0 0.0 0.0 0.0 0.0 0.01539199985563755 0.040031999349594116 0.0212032001465559 0.01649599988013506 0.008068547381446682 0.0 0.0 0.0 0.0 0.0 0.06588800251483917 0.07897599786520004 0.0703904002904892 0.0703904002904892 0.004214826869769361 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
200 0.0 0.0 0.0 0.0 0.0 0.014495999552309513 0.022495999932289124 0.016006399970501663 0.01515199989080429 0.002265581884342885 0.0 0.0 0.0 0.0 0.0 0.1231679990887642 0.13526399433612823 0.1288223996758461 0.1288223996758461 0.004328976434897094 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
201 0.0 0.0 0.0 0.0 0.0 0.014592000283300877 0.023231999948620796 0.01705600004643202 0.016048000194132328 0.002810904312746391 0.0 0.0 0.0 0.0 0.0 0.3158079981803894 0.33129599690437317 0.32348800003528594 0.32348800003528594 0.00417599076136664 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
202 0.0 0.0 0.0 0.0 0.0 0.014527999795973301 0.021888000890612602 0.01708160014823079 0.01609600055962801 0.0025289234621475062 0.0 0.0 0.0 0.0 0.0 0.5103679895401001 0.5200319886207581 0.5132320046424866 0.5132320046424866 0.0035759433157749533 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
203 0.0 0.0 0.0 0.0 0.0 0.014688000082969666 0.032416000962257385 0.019353600032627583 0.016176000237464905 0.0061458798960684425 0.0 0.0 0.0 0.0 0.0 0.7400320172309875 0.7516480088233948 0.7449311971664427 0.7449311971664427 0.004573461776168607 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 32768.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
204 0.0 0.0 0.0 0.0 0.0 0.0144640002399683 0.02006400004029274 0.01573119992390275 0.014992000069469213 0.001654446341262991 0.0 0.0 0.0 0.0 0.0 0.07097599655389786 0.09932799637317657 0.07828159928321837 0.07828159928321837 0.009464602895232642 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1] 1 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
205 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.02319999970495701 0.016883199848234654 0.015775999519973993 0.0026693906156048403 0.0 0.0 0.0 0.0 0.0 0.14176000654697418 0.1598079949617386 0.15063679963350293 0.15063679963350293 0.005741662969679433 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 8 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1] 8 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 8q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
206 0.0 0.0 0.0 0.0 0.0 0.01484800036996603 0.03203200176358223 0.022224000189453363 0.02247999981045723 0.005996176183124981 0.0 0.0 0.0 0.0 0.0 0.39180800318717957 0.41046398878097534 0.4003200054168701 0.4003200054168701 0.005552433764307601 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 16 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 16 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 16q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
207 0.0 0.0 0.0 0.0 0.0 0.015072000212967396 0.028192000463604927 0.017152000125497578 0.015536000020802021 0.003847486121602065 0.0 0.0 0.0 0.0 0.0 0.6239359974861145 0.6367359757423401 0.6285343945026398 0.6285343945026398 0.004006084286606002 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 32 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 32 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 32q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
208 0.0 0.0 0.0 0.0 0.0 0.014879999682307243 0.026688000187277794 0.01718079997226596 0.015488000120967627 0.0037132536813398722 0.0 0.0 0.0 0.0 0.0 0.9141119718551636 0.9721279740333557 0.927455997467041 0.927455997467041 0.02148767779232235 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 64 0 40960.0 False FLASH_ATTN False vllm020_batch_spec [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] 64 1 1 1.0 True 0.0 0.0 0.0 False 0 0 0 BF16 generic none CUDA_EVENT False 64q1s40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
209 0.0 0.0 0.0 0.0 0.0 0.014751999638974667 0.047520000487565994 0.028710400220006704 0.0266720000654459 0.010774688401598903 0.06094816381288764 0.06816969726785131 0.0644060660218149 0.0644060660218149 0.002203106589073183 0.087051838094461 0.09736630405680231 0.09199073574791852 0.09199073574791852 0.0031466818046499644 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 9 0 0 True FLASH_ATTN False true_mixed_fused_projected 520 False 512 BF16 generic none CUDA_EVENT True [512] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 8 8 9 8 16384.0 0.1111111111111111 q512_8q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
210 0.0 0.0 0.0 0.0 0.0 0.014911999925971031 0.02489599958062172 0.017427200078964235 0.01595200039446354 0.003071906489592143 0.19733789497223914 0.2016295616652644 0.19860388994013833 0.19860388994013833 0.001512389485439305 0.44861409134062713 0.45837046456077934 0.45149211526120153 0.45149211526120153 0.0034381598874302305 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 1040 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 16 16 17 16 16384.0 0.058823529411764705 q1k_16q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
211 0.0 0.0 0.0 0.0 0.0 0.015039999969303608 0.03046399913728237 0.020643199887126686 0.016944000497460365 0.006320148675595729 0.2157924314537054 0.22215709640166995 0.21769400765743155 0.21769400765743155 0.0019679921844645526 0.4905115822753901 0.5049789194903589 0.4948340005651485 0.4948340005651485 0.0044733865493072344 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384] 1 32 32 33 32 16384.0 0.030303030303030304 q2k_32q1s16k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
212 0.0 0.0 0.0 0.0 0.0 0.017152000218629837 0.02425600029528141 0.01865920014679432 0.018112000077962875 0.0019454553198986453 0.7430866512973927 0.7578834738720781 0.7455351005236347 0.7455351005236347 0.00416692487556653 0.7369773831645824 0.7516525540362471 0.7394057025273603 0.7394057025273603 0.004132666607961175 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 17 0 0 True FLASH_ATTN False true_mixed_fused_projected 4112 False 4096 BF16 generic none CUDA_EVENT True [4096] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 16 16 17 16 32768.0 0.058823529411764705 q4k_16q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
213 0.0 0.0 0.0 0.0 0.0 0.015263999812304974 0.02470399998128414 0.018009600043296815 0.01657600048929453 0.0031544532774534346 0.25251173919752334 0.25566890792461106 0.2536729054481981 0.2536729054481981 0.0010279562245342983 1.0425282722084215 1.0555630628624373 1.0473223013846877 1.0473223013846877 0.004244053880724073 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 33 0 0 True FLASH_ATTN False true_mixed_fused_projected 2080 False 2048 BF16 generic none CUDA_EVENT True [2048] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 32 32 33 32 32768.0 0.030303030303030304 q2k_32q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
214 0.0 0.0 0.0 0.0 0.0 0.01500799972563982 0.027807999402284622 0.01912960009649396 0.01643200032413006 0.004688164695934997 0.1251379565220268 0.14341821167748953 0.12742497577885914 0.12742497577885914 0.005353812167343766 1.1355340167064276 1.3014137556763312 1.1562870179154463 1.1562870179154463 0.048581869194943325 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 65 0 0 True FLASH_ATTN False true_mixed_fused_projected 1088 False 1024 BF16 generic none CUDA_EVENT True [1024] [0] [32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768, 32768] 1 64 64 65 64 32768.0 0.015384615384615385 q1k_64q1s32k fused_total_conserving_projection_by_same_tp_pure_prefill_decode_reference_ratio
215 0.0 0.0 0.0 0.0 0.0 0.07446400076150894 0.08246400207281113 0.07736000046133995 0.07713599875569344 0.002301031358835964 11.935359954833984 12.102368354797363 11.96896333694458 11.96896333694458 0.05162549713370252 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 8192 8192.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 8192.0 16384.0 8192 BF16 generic none CUDA_EVENT False q8ks16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
216 0.0 0.0 0.0 0.0 0.0 0.07664000242948532 0.08118399977684021 0.07796800062060356 0.077504001557827 0.0013681081693640953 19.84774398803711 20.15795135498047 19.915702438354494 19.915702438354494 0.0912299324030902 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 8192 16384.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 16384.0 24576.0 8192 BF16 generic none CUDA_EVENT False q8ks24k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
217 0.0 0.0 0.0 0.0 0.0 0.0753600001335144 0.08207999914884567 0.07715519964694977 0.07595199719071388 0.0024238358447475007 27.781503677368164 27.9836483001709 27.844886589050287 27.844886589050287 0.061307010154819624 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 8192 24576.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 24576.0 32768.0 8192 BF16 generic none CUDA_EVENT False q8ks32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
218 0.0 0.0 0.0 0.0 0.0 0.04339199885725975 0.050016000866889954 0.04504639990627766 0.04391999915242195 0.002339637813151782 5.1544318199157715 5.269279956817627 5.16938238143921 5.16938238143921 0.03363105774712194 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 4096 8192.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 8192.0 12288.0 4096 BF16 generic none CUDA_EVENT False q4ks12k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
219 0.0 0.0 0.0 0.0 0.0 0.04291199892759323 0.058848001062870026 0.045657599717378615 0.04383999854326248 0.004522763233004815 9.256383895874023 9.27734375 9.261776161193849 9.261776161193849 0.0062232312957398745 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 4096 16384.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 16384.0 20480.0 4096 BF16 generic none CUDA_EVENT False q4ks20k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
220 0.0 0.0 0.0 0.0 0.0 0.043296001851558685 0.04982399940490723 0.045123199746012685 0.04387199878692627 0.0023369398894319345 13.365216255187988 13.634464263916016 13.398719978332519 13.398719978332519 0.0787651922310212 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 4096 24576.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 24576.0 28672.0 4096 BF16 generic none CUDA_EVENT False q4ks28k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
221 0.0 0.0 0.0 0.0 0.0 0.02703999914228916 0.0297279991209507 0.027692800015211107 0.02723200060427189 0.000851127720159845 2.387968063354492 2.4014720916748047 2.3920736074447637 2.3920736074447637 0.003552645719470337 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 2048 8192.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 8192.0 10240.0 2048 BF16 generic none CUDA_EVENT False q2ks10k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
222 0.0 0.0 0.0 0.0 0.0 0.02691200003027916 0.029823999851942062 0.027689599990844728 0.027583999559283257 0.0007783369959809023 4.440767765045166 4.4521918296813965 4.444268751144409 4.444268751144409 0.004022325406840951 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 2048 16384.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 16384.0 18432.0 2048 BF16 generic none CUDA_EVENT False q2ks18k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
223 0.0 0.0 0.0 0.0 0.0 0.02703999914228916 0.03888000175356865 0.030262400023639204 0.02801600005477667 0.0037877256209144718 6.500351905822754 6.600607872009277 6.524902391433716 6.524902391433716 0.03321667087212851 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 2048 24576.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 24576.0 26624.0 2048 BF16 generic none CUDA_EVENT False q2ks26k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
224 0.0 0.0 0.0 0.0 0.0 0.07865600287914276 0.08668799698352814 0.08130879923701287 0.07993599772453308 0.0027016201268628523 35.717376708984375 35.843265533447266 35.771837615966795 35.771837615966795 0.04024815379149301 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 40960 1 8192 32768.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 32768.0 40960.0 8192 BF16 generic none CUDA_EVENT False q8ks40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
225 0.0 0.0 0.0 0.0 0.0 0.04179200157523155 0.04864000156521797 0.0436256006360054 0.04267200082540512 0.002191476789190783 6.103871822357178 6.18287992477417 6.118390369415283 6.118390369415283 0.022924175047267112 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 8192 8192.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 8192.0 16384.0 8192 BF16 generic none CUDA_EVENT False q8ks16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
226 0.0 0.0 0.0 0.0 0.0 0.04163200035691261 0.05987200140953064 0.04625920057296753 0.04403200000524521 0.005544136325859629 10.207136154174805 11.073247909545898 10.326777648925782 10.326777648925782 0.25139335734700863 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 8192 16384.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 16384.0 24576.0 8192 BF16 generic none CUDA_EVENT False q8ks24k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
227 0.0 0.0 0.0 0.0 0.0 0.04137599840760231 0.05027199909090996 0.04355199970304966 0.042399998754262924 0.0026572716942034787 14.303423881530762 14.343520164489746 14.311049747467042 14.311049747467042 0.01137511287661936 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 8192 24576.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 24576.0 32768.0 8192 BF16 generic none CUDA_EVENT False q8ks32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
228 0.0 0.0 0.0 0.0 0.0 0.026016000658273697 0.03718400001525879 0.03212799951434135 0.03270399942994118 0.003953184738275612 2.6534719467163086 2.6875839233398438 2.661257576942444 2.661257576942444 0.009372641904054613 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 4096 8192.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 8192.0 12288.0 4096 BF16 generic none CUDA_EVENT False q4ks12k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
229 0.0 0.0 0.0 0.0 0.0 0.025887999683618546 0.03347200155258179 0.027168000116944313 0.02649599965661764 0.0021492000999850562 4.70630407333374 4.7400641441345215 4.714492845535279 4.714492845535279 0.009349196197962609 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 4096 16384.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 16384.0 20480.0 4096 BF16 generic none CUDA_EVENT False q4ks20k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
230 0.0 0.0 0.0 0.0 0.0 0.025631999596953392 0.030719999223947525 0.02736639976501465 0.02711999975144863 0.0013921874495504173 6.759712219238281 6.831999778747559 6.774675178527832 6.774675178527832 0.021507023842020512 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 4096 24576.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 24576.0 28672.0 4096 BF16 generic none CUDA_EVENT False q4ks28k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
231 0.0 0.0 0.0 0.0 0.0 0.017855999991297722 0.024831999093294144 0.01991359982639551 0.018655999563634396 0.0023971416189370203 1.3446400165557861 1.3609600067138672 1.3508928060531615 1.3508928060531615 0.006186954712541735 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 2048 8192.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 8192.0 10240.0 2048 BF16 generic none CUDA_EVENT False q2ks10k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
232 0.0 0.0 0.0 0.0 0.0 0.0180479995906353 0.022752000018954277 0.019507200084626676 0.01896000001579523 0.0015079573553847933 2.5208001136779785 2.5887041091918945 2.534086418151855 2.534086418151855 0.01891953046799999 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 2048 16384.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 16384.0 18432.0 2048 BF16 generic none CUDA_EVENT False q2ks18k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
233 0.0 0.0 0.0 0.0 0.0 0.018144000321626663 0.03222399950027466 0.02052800003439188 0.018864000216126442 0.004114364828004189 3.6922879219055176 3.760576009750366 3.706630396842957 3.706630396842957 0.019888657921309623 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 2048 24576.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 24576.0 26624.0 2048 BF16 generic none CUDA_EVENT False q2ks26k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
234 0.0 0.0 0.0 0.0 0.0 0.04169600084424019 0.04822399839758873 0.0439775999635458 0.04334400035440922 0.002101844179466219 18.41494369506836 18.502975463867188 18.445004844665526 18.445004844665526 0.026939913540867878 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 40960 1 8192 32768.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 32768.0 40960.0 8192 BF16 generic none CUDA_EVENT False q8ks40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
235 0.0 0.0 0.0 0.0 0.0 0.023615999147295952 0.03267199918627739 0.026281599886715412 0.0248800003901124 0.003167969318232417 3.1188158988952637 3.1837120056152344 3.133536005020142 3.133536005020142 0.018365009771617643 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 8192 8192.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 8192.0 16384.0 8192 BF16 generic none CUDA_EVENT False q8ks16k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
236 0.0 0.0 0.0 0.0 0.0 0.02380800060927868 0.03283200040459633 0.025670399703085423 0.024639999493956566 0.0026095917641781453 5.1729278564453125 5.243135929107666 5.192828798294067 5.192828798294067 0.01984737475315108 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 8192 16384.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 16384.0 24576.0 8192 BF16 generic none CUDA_EVENT False q8ks24k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
237 0.0 0.0 0.0 0.0 0.0 0.024032000452280045 0.03167999908328056 0.02665280010551214 0.02550400048494339 0.002510131946267113 7.223167896270752 7.257152080535889 7.231532812118529 7.231532812118529 0.009418898846297825 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 8192 24576.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 24576.0 32768.0 8192 BF16 generic none CUDA_EVENT False q8ks32k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
238 0.0 0.0 0.0 0.0 0.0 0.01696000061929226 0.023679999634623528 0.01866880003362894 0.017455999739468098 0.002277860345236006 1.478559970855713 1.496127963066101 1.48257919549942 1.48257919549942 0.005278358037488471 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 4096 8192.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 8192.0 12288.0 4096 BF16 generic none CUDA_EVENT False q4ks12k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
239 0.0 0.0 0.0 0.0 0.0 0.017023999243974686 0.030688000842928886 0.02055360022932291 0.018240000121295452 0.004065815389665311 2.651711940765381 2.6691839694976807 2.657548785209656 2.657548785209656 0.005897264516465086 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 4096 16384.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 16384.0 20480.0 4096 BF16 generic none CUDA_EVENT False q4ks20k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
240 0.0 0.0 0.0 0.0 0.0 0.016767999157309532 0.024351999163627625 0.01840319987386465 0.017167999409139156 0.0025234367788448957 3.823551893234253 3.8631999492645264 3.8335999727249135 3.8335999727249135 0.011858923917429712 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 4096 24576.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 24576.0 28672.0 4096 BF16 generic none CUDA_EVENT False q4ks28k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
241 0.0 0.0 0.0 0.0 0.0 0.013952000066637993 0.03622400015592575 0.018214400112628936 0.014719999860972166 0.007277897466521675 0.7039039731025696 0.7163199782371521 0.7077983975410462 0.7077983975410462 0.004048424224033295 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 2048 8192.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 8192.0 10240.0 2048 BF16 generic none CUDA_EVENT False q2ks10k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
242 0.0 0.0 0.0 0.0 0.0 0.015104000456631184 0.03097599931061268 0.020870400313287973 0.02054399996995926 0.005422197456220526 1.2929600477218628 1.313088059425354 1.3006752014160157 1.3006752014160157 0.00790622446009414 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 2048 16384.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 16384.0 18432.0 2048 BF16 generic none CUDA_EVENT False q2ks18k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
243 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.03232000023126602 0.019132800027728082 0.01673599984496832 0.0050857949387988245 1.8775999546051025 1.9125759601593018 1.8867840051651 1.8867840051651 0.01196043526228758 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 2048 24576.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 24576.0 26624.0 2048 BF16 generic none CUDA_EVENT False q2ks26k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
244 0.0 0.0 0.0 0.0 0.0 0.023584000766277313 0.03126399964094162 0.02633600030094385 0.025200000032782555 0.0025710957466677864 9.283391952514648 9.48249626159668 9.331705665588379 9.331705665588379 0.06366970422148335 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 40960 1 8192 32768.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 32768.0 40960.0 8192 BF16 generic none CUDA_EVENT False q8ks40k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
245 0.0 0.0 0.0 0.0 0.0 0.07552000135183334 0.0851840004324913 0.07839040011167527 0.07703999802470207 0.0030805904904383677 43.62025451660156 43.89299011230469 43.68390693664551 43.68390693664551 0.08458163192147439 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 40960.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 40960.0 49152.0 8192 BF16 generic none CUDA_EVENT False q8ks48k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
246 0.0 0.0 0.0 0.0 0.0 0.07718399912118912 0.0854400023818016 0.07895359992980958 0.07791999727487564 0.0024425064759109735 59.421791076660156 59.73017501831055 59.5021312713623 59.5021312713623 0.10367381308510447 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 57344.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 57344.0 65536.0 8192 BF16 generic none CUDA_EVENT False q8ks64k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
247 0.0 0.0 0.0 0.0 0.0 0.07875200361013412 0.09055999666452408 0.08208959847688675 0.08087999746203423 0.0033614630055883482 75.2852783203125 75.55481719970703 75.38758392333985 75.38758392333985 0.08870109119325344 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 73728.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 73728.0 81920.0 8192 BF16 generic none CUDA_EVENT False q8ks80k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
248 0.0 0.0 0.0 0.0 0.0 0.07788799703121185 0.09888000041246414 0.0819871999323368 0.08008000254631042 0.005835618489111142 91.13442993164062 91.45164489746094 91.24225158691405 91.24225158691405 0.1009018902177725 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 90112.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 90112.0 98304.0 8192 BF16 generic none CUDA_EVENT False q8ks96k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
249 0.0 0.0 0.0 0.0 0.0 0.07596799731254578 0.08790399879217148 0.07967040091753005 0.07808000221848488 0.0036209252740976605 106.89055633544922 107.34063720703125 106.9560287475586 106.9560287475586 0.13032874360676439 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 106496.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 106496.0 114688.0 8192 BF16 generic none CUDA_EVENT False q8ks112k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
250 0.0 0.0 0.0 0.0 0.0 0.07648000121116638 0.08534400165081024 0.07928640022873878 0.07787200063467026 0.0028305104107121735 122.71724700927734 122.9840316772461 122.8334243774414 122.8334243774414 0.09625274868603513 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 122880.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 122880.0 131072.0 8192 BF16 generic none CUDA_EVENT False q8ks128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
251 0.0 0.0 0.0 0.0 0.0 0.07664000242948532 0.08774399757385254 0.08081279993057251 0.07972799986600876 0.003487270970977775 130.6565399169922 131.09359741210938 130.79229431152345 130.79229431152345 0.13138911961272914 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 8192 131072.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 131072.0 139264.0 8192 BF16 generic none CUDA_EVENT False q8ks136k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
252 0.0 0.0 0.0 0.0 0.0 0.01532800029963255 0.040063999593257904 0.019459199998527764 0.01601599995046854 0.007496165774486326 9.443936347961426 9.649087905883789 9.489968109130858 9.489968109130858 0.05961646816296781 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 512 130560.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 130560.0 131072.0 512 BF16 generic none CUDA_EVENT False q512s128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
253 0.0 0.0 0.0 0.0 0.0 0.02691200003027916 0.040832001715898514 0.02942080032080412 0.027888000011444092 0.004040048279091587 16.753759384155273 16.90662384033203 16.78766403198242 16.78766403198242 0.04236470233451937 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 2048 65536.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 65536.0 67584.0 2048 BF16 generic none CUDA_EVENT False q2ks66k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
254 0.0 0.0 0.0 0.0 0.0 0.04416000097990036 0.04867200180888176 0.04565120078623295 0.04468800127506256 0.0018079971851529544 50.29715347290039 50.50300979614258 50.35054740905761 50.35054740905761 0.0724480602714254 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 4096 98304.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 98304.0 102400.0 4096 BF16 generic none CUDA_EVENT False q4ks100k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
255 0.0 0.0 0.0 0.0 0.0 0.060447998344898224 0.06684800237417221 0.06276160031557083 0.061824001371860504 0.0024045636532566625 96.07142639160156 96.53209686279297 96.1898666381836 96.1898666381836 0.1365794879996899 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 1 147456 1 6144 131072.0 True FLASH_ATTN False vllm020_batch_spec [6144] 6144 6144 6144 6144.0 True 0.0 0.0 0.0 True 131072.0 137216.0 6144 BF16 generic none CUDA_EVENT False q6ks134k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
256 0.0 0.0 0.0 0.0 0.0 0.04217600077390671 0.05100800096988678 0.04406719990074635 0.042847998440265656 0.002656672983576728 22.5166072845459 22.986656188964844 22.63068161010742 22.63068161010742 0.13840494695459715 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 40960.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 40960.0 49152.0 8192 BF16 generic none CUDA_EVENT False q8ks48k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
257 0.0 0.0 0.0 0.0 0.0 0.04182400181889534 0.047200001776218414 0.043644800409674646 0.04262400045990944 0.001927741871473188 30.725727081298828 30.787456512451172 30.74285774230957 30.74285774230957 0.019110324860515015 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 57344.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 57344.0 65536.0 8192 BF16 generic none CUDA_EVENT False q8ks64k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
258 0.0 0.0 0.0 0.0 0.0 0.04185599833726883 0.05049600079655647 0.043852799385786054 0.04289599880576134 0.0024573088797598033 38.930206298828125 38.98448181152344 38.94538269042969 38.94538269042969 0.017734743323340796 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 73728.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 73728.0 81920.0 8192 BF16 generic none CUDA_EVENT False q8ks80k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
259 0.0 0.0 0.0 0.0 0.0 0.04227200150489807 0.046911999583244324 0.04412479996681214 0.04327999986708164 0.001811858548765738 47.13151931762695 47.245887756347656 47.148198699951166 47.148198699951166 0.033297799765613076 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 90112.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 90112.0 98304.0 8192 BF16 generic none CUDA_EVENT False q8ks96k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
260 0.0 0.0 0.0 0.0 0.0 0.04182400181889534 0.06195199862122536 0.04529919996857643 0.043136000633239746 0.005751677082163394 55.338497161865234 55.64672088623047 55.42207336425782 55.42207336425782 0.11010194068839292 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 106496.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 106496.0 114688.0 8192 BF16 generic none CUDA_EVENT False q8ks112k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
261 0.0 0.0 0.0 0.0 0.0 0.04182400181889534 0.054687999188899994 0.04418559968471527 0.042767999693751335 0.0036820249064621804 63.549087524414055 63.80697631835938 63.62084197998047 63.62084197998047 0.08872184973119365 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 122880.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 122880.0 131072.0 8192 BF16 generic none CUDA_EVENT False q8ks128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
262 0.0 0.0 0.0 0.0 0.0 0.0461760014295578 0.06566400080919266 0.05008000023663044 0.04843199998140335 0.0055350567765421 67.64147186279297 67.91651153564453 67.70619888305666 67.70619888305666 0.0993520482760623 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 8192 131072.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 131072.0 139264.0 8192 BF16 generic none CUDA_EVENT False q8ks136k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
263 0.0 0.0 0.0 0.0 0.0 0.023711999878287315 0.03859199956059456 0.02689919974654913 0.0244159996509552 0.004626699769228834 4.775519847869873 4.829855918884277 4.790303993225097 4.790303993225097 0.01597276061319242 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 512 130560.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 130560.0 131072.0 512 BF16 generic none CUDA_EVENT False q512s128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
264 0.0 0.0 0.0 0.0 0.0 0.024224000051617622 0.0453759990632534 0.027676799893379213 0.025200000032782555 0.006154880946840619 9.579392433166504 9.63871955871582 9.59802885055542 9.59802885055542 0.016811667352984866 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 2048 65536.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 65536.0 67584.0 2048 BF16 generic none CUDA_EVENT False q2ks66k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
265 0.0 0.0 0.0 0.0 0.0 0.02630399912595749 0.03593600168824196 0.02780479993671179 0.027040000073611736 0.0027569987978884785 25.21686363220215 25.383039474487305 25.250255966186526 25.250255966186526 0.04761963064809279 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 4096 98304.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 98304.0 102400.0 4096 BF16 generic none CUDA_EVENT False q4ks100k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
266 0.0 0.0 0.0 0.0 0.0 0.034015998244285583 0.041728001087903976 0.03665280006825924 0.0352960005402565 0.002710617869728372 48.101280212402344 48.49884796142578 48.17219200134278 48.17219200134278 0.11195495368044632 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 2 147456 1 6144 131072.0 True FLASH_ATTN False vllm020_batch_spec [6144] 6144 6144 6144 6144.0 True 0.0 0.0 0.0 True 131072.0 137216.0 6144 BF16 generic none CUDA_EVENT False q6ks134k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
267 0.0 0.0 0.0 0.0 0.0 0.024191999807953835 0.039583999663591385 0.027286400087177753 0.025200000032782555 0.004620118437533604 11.32140827178955 11.496224403381348 11.354345512390138 11.354345512390138 0.050117766215439966 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 40960.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 40960.0 49152.0 8192 BF16 generic none CUDA_EVENT False q8ks48k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
268 0.0 0.0 0.0 0.0 0.0 0.024032000452280045 0.03232000023126602 0.026406400091946124 0.02518399991095066 0.002792696117638337 15.42249584197998 15.639776229858397 15.451993656158448 15.451993656158448 0.06304729308178388 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 57344.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 57344.0 65536.0 8192 BF16 generic none CUDA_EVENT False q8ks64k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
269 0.0 0.0 0.0 0.0 0.0 0.024224000051617622 0.03488000109791756 0.026147199980914592 0.02459200005978346 0.003303059079404486 19.5251522064209 19.70569610595703 19.54985942840576 19.54985942840576 0.052248914965338324 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 73728.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 73728.0 81920.0 8192 BF16 generic none CUDA_EVENT False q8ks80k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
270 0.0 0.0 0.0 0.0 0.0 0.024159999564290047 0.03046399913728237 0.0255103999748826 0.024656000547111034 0.00195717586616911 23.630016326904297 23.927040100097656 23.672822570800783 23.672822570800783 0.08715594728873713 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 90112.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 90112.0 98304.0 8192 BF16 generic none CUDA_EVENT False q8ks96k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
271 0.0 0.0 0.0 0.0 0.0 0.02380800060927868 0.03574400022625923 0.02678720001131296 0.024720000103116035 0.003678231234048846 27.736671447753906 27.79840087890625 27.747158622741697 27.747158622741697 0.018952179343788657 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 106496.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 106496.0 114688.0 8192 BF16 generic none CUDA_EVENT False q8ks112k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
272 0.0 0.0 0.0 0.0 0.0 0.024224000051617622 0.042080000042915344 0.02844479978084564 0.02527999971061945 0.006562862750709003 31.83427238464356 32.08835220336914 31.86994876861572 31.86994876861572 0.07444245241186317 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 122880.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 122880.0 131072.0 8192 BF16 generic none CUDA_EVENT False q8ks128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
273 0.0 0.0 0.0 0.0 0.0 0.02377600036561489 0.03139200061559677 0.026396799832582474 0.025071999989449978 0.0025962810796740263 33.88313674926758 33.96985626220703 33.89708137512208 33.89708137512208 0.02518493598134421 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 8192 131072.0 True FLASH_ATTN False vllm020_batch_spec [8192] 8192 8192 8192 8192.0 True 0.0 0.0 0.0 True 131072.0 139264.0 8192 BF16 generic none CUDA_EVENT False q8ks136k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
274 0.0 0.0 0.0 0.0 0.0 0.014944000169634819 0.022624000906944275 0.017174400109797715 0.015536000020802021 0.0028331860349340154 3.179744005203247 3.192960023880005 3.182867193222046 3.182867193222046 0.0035239767128429386 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 512 130560.0 True FLASH_ATTN False vllm020_batch_spec [512] 512 512 512 512.0 True 0.0 0.0 0.0 True 130560.0 131072.0 512 BF16 generic none CUDA_EVENT False q512s128k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
275 0.0 0.0 0.0 0.0 0.0 0.014655999839305878 0.02985600009560585 0.017318400088697672 0.015568000264465809 0.004479309643844885 4.811935901641846 4.826848030090332 4.8173023700714115 4.8173023700714115 0.00594674080057053 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 2048 65536.0 True FLASH_ATTN False vllm020_batch_spec [2048] 2048 2048 2048 2048.0 True 0.0 0.0 0.0 True 65536.0 67584.0 2048 BF16 generic none CUDA_EVENT False q2ks66k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
276 0.0 0.0 0.0 0.0 0.0 0.017184000462293625 0.03916800022125244 0.021356799826025962 0.01935999933630228 0.0062801287963799276 14.374591827392578 14.635007858276367 14.41227512359619 14.41227512359619 0.07569270440104603 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 4096 98304.0 True FLASH_ATTN False vllm020_batch_spec [4096] 4096 4096 4096 4096.0 True 0.0 0.0 0.0 True 98304.0 102400.0 4096 BF16 generic none CUDA_EVENT False q4ks100k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median
277 0.0 0.0 0.0 0.0 0.0 0.020479999482631683 0.033215999603271484 0.023340800032019614 0.02092800009995699 0.004304974035052475 24.088096618652344 24.18492889404297 24.11243553161621 24.11243553161621 0.02797845886790172 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2048 32 4 16 4 147456 1 6144 131072.0 True FLASH_ATTN False vllm020_batch_spec [6144] 6144 6144 6144 6144.0 True 0.0 0.0 0.0 True 131072.0 137216.0 6144 BF16 generic none CUDA_EVENT False q6ks134k measured_FA3_core_plus_measured_KV;reshape_assumed_zero;mean_as_median

View File

@@ -0,0 +1,37 @@
time_stats.emb.min,time_stats.emb.max,time_stats.emb.mean,time_stats.emb.median,time_stats.emb.std,time_stats.input_layernorm.min,time_stats.input_layernorm.max,time_stats.input_layernorm.mean,time_stats.input_layernorm.median,time_stats.input_layernorm.std,time_stats.attn_pre_proj.min,time_stats.attn_pre_proj.max,time_stats.attn_pre_proj.mean,time_stats.attn_pre_proj.median,time_stats.attn_pre_proj.std,time_stats.attn_rope.min,time_stats.attn_rope.max,time_stats.attn_rope.mean,time_stats.attn_rope.median,time_stats.attn_rope.std,time_stats.attn_post_proj.min,time_stats.attn_post_proj.max,time_stats.attn_post_proj.mean,time_stats.attn_post_proj.median,time_stats.attn_post_proj.std,time_stats.post_attention_layernorm.min,time_stats.post_attention_layernorm.max,time_stats.post_attention_layernorm.mean,time_stats.post_attention_layernorm.median,time_stats.post_attention_layernorm.std,n_head,n_kv_head,n_embd,n_expanded_embd,vocab_size,use_gated_mlp,use_qk_norm,attn_output_gate,num_tokens,num_tensor_parallel_workers,padded_n_embd,padded_n_expanded_embd,model_arch,is_step2_mini,share_expert_dim,share_q_dim,measurement_type,profiling_precision,quant_signature
0.029184000566601753,0.06780800223350525,0.03157280012965202,0.030736000277101994,0.005874173435341216,0.033215999603271484,0.04825599864125252,0.03443359974771738,0.0337119996547699,0.0031825678429048183,1.438431978225708,1.505568027496338,1.446228802204132,1.4429279565811157,0.014128607642643025,0.538752019405365,0.5440319776535034,0.5416463971138,0.5420799851417542,0.0016099306164432847,1.0073280334472656,1.0163840055465698,1.0098415970802308,1.0081279873847961,0.0032980457197329728,0.04022400081157684,0.041728001087903976,0.04091359991580248,0.04081599973142147,0.0004728505416767937,32,4,2048,768,151936,True,True,False,8192,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.01360000018030405,0.06784000247716904,0.017755200061947106,0.0179840000346303,0.00837681421401443,0.01836800016462803,0.03651199862360954,0.019606399815529585,0.018719999119639397,0.0038821958848767424,0.7512000203132629,0.8208960294723511,0.7566704005002975,0.75382399559021,0.014793092586577971,0.28995200991630554,0.29337599873542786,0.29135999977588656,0.29150401055812836,0.000998381071258815,0.5149760246276855,0.5169600248336792,0.5160208016633987,0.5158880054950714,0.0005038652783291977,0.02051199972629547,0.021503999829292297,0.021067200042307378,0.021104000508785248,0.00023542855306902367,32,4,2048,768,151936,True,True,False,4096,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.0080960001796484,0.04281599819660187,0.011092799971811474,0.011039999779313803,0.005489135752949302,0.012223999947309494,0.026335999369621277,0.013187199970707298,0.01247999956831336,0.0030236510562153375,0.3928639888763428,0.45372799038887024,0.3976895987987518,0.39528000354766846,0.012905176716136006,0.1547199934720993,0.15884800255298615,0.15712319910526276,0.1573439985513687,0.001165121945135037,0.26633599400520325,0.268095999956131,0.26719200164079665,0.2671840041875839,0.0004242740199415328,0.013024000450968742,0.013887999579310417,0.013489600038155913,0.013520000036805868,0.0002382817554057738,32,4,2048,768,151936,True,True,False,2048,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.00825599953532219,0.04755200073122978,0.02398160002194345,0.01961600035429001,0.00874683840888523,0.018880000337958336,0.03868800029158592,0.021590400114655496,0.0208320003002882,0.004057015751746236,0.24316799640655518,0.2710399925708771,0.2521967992186546,0.25065599381923676,0.007998418528894075,0.09644799679517746,0.19120000302791595,0.10407840013504029,0.09963199868798256,0.020043722414992166,0.13600000739097595,0.18892799317836761,0.15760480016469955,0.15760000050067902,0.0112223677907762,0.009664000011980534,0.010015999898314476,0.009836799977347255,0.009824000298976898,9.016971952948177e-05,32,4,2048,768,151936,True,True,False,1024,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017376000061631203,0.044704001396894455,0.026318399980664254,0.027312000282108784,0.007565344034680866,0.01836800016462803,0.03014400042593479,0.021276800055056812,0.020655999891459942,0.002632977855097951,0.1438719928264618,0.17132799327373505,0.152497598528862,0.15012799948453903,0.007947150319625347,0.1430719941854477,0.19305600225925446,0.16630879789590836,0.1685439944267273,0.014628024163894684,0.08899199962615967,0.10467199981212616,0.0943599995225668,0.09374399855732918,0.003472669494074113,0.007615999784320593,0.007935999892652035,0.007769599952735007,0.0077760000713169575,7.680004540222077e-05,32,4,2048,768,151936,True,True,False,512,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.016992000862956047,0.0544000007212162,0.02573199989274144,0.026016000658273697,0.00803323401720434,0.018432000651955605,0.02348800003528595,0.020648000109940768,0.02062400057911873,0.0013939985047930988,0.10220800340175629,0.1361600011587143,0.11850560046732425,0.11684799939393997,0.010637754898360304,0.16710400581359863,0.21110400557518005,0.19078560024499894,0.19409599900245667,0.013714352646558832,0.06265600025653839,0.0740479975938797,0.06842879951000214,0.0690080001950264,0.0031292240446560557,0.00979200005531311,0.033440001308918,0.01864320016466081,0.017280000261962414,0.006957998188876383,32,4,2048,768,151936,True,True,False,256,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017152000218629837,0.04396799951791763,0.025907999789342284,0.02598400041460991,0.007714554737915267,0.018400000408291817,0.03667199984192848,0.024132800102233887,0.02112000063061714,0.006120348733354326,0.10678400099277496,0.1363839954137802,0.1193264003843069,0.11583999916911125,0.009838647443214228,0.17017599940299988,0.22748799622058868,0.18853759989142418,0.18433599919080734,0.015728078443174653,0.04569600149989128,0.06652799993753433,0.05192639995366335,0.05151999928057194,0.004516605694976449,0.021856000646948814,0.026335999369621277,0.02384479995816946,0.023599999956786633,0.0011301153013314744,32,4,2048,768,151936,True,True,False,128,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017343999817967415,1.0683200359344482,0.05748240072280168,0.029504000209271908,0.16366824814254827,0.018688000738620758,0.3317759931087494,0.03685439983382821,0.021151999942958355,0.06767422466731164,0.10255999863147736,0.9434880018234253,0.16412640027701855,0.11956800147891045,0.17964606281728834,0.1714559942483902,2.1306240558624268,0.3011296011507511,0.1926399990916252,0.42310127734378766,0.03574400022625923,0.6859520077705383,0.08389280084520578,0.04279999993741512,0.14321647071615612,0.020479999482631683,0.1831360012292862,0.033024000097066165,0.023856000043451786,0.03470987082429836,32,4,2048,768,151936,True,True,False,64,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.016095999628305435,0.05142400041222572,0.026363200135529043,0.02676799986511469,0.008637725852473854,0.01849599927663803,0.03577600046992302,0.022193600237369538,0.020848000422120094,0.004615266181181815,0.10540799796581268,0.15014399588108063,0.12211520001292228,0.11896000057458878,0.012772013396624768,0.17315199971199036,0.21478399634361267,0.1881632000207901,0.1873439997434616,0.011761164657572015,0.03481600061058998,0.058079998940229416,0.042200000025331974,0.03969600051641464,0.006461281521769989,0.02143999934196472,0.038816001266241074,0.02466559996828437,0.023856000043451786,0.0035418033748569927,32,4,2048,768,151936,True,True,False,32,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.015904000028967857,0.03753599897027016,0.023127999808639287,0.02527999971061945,0.0054230027890305385,0.018400000408291817,0.03001599945127964,0.020488000102341176,0.020096000283956528,0.002585688394137697,0.10355199873447418,0.1438400000333786,0.11536479964852334,0.11124800145626068,0.011136028294919255,0.16502399742603302,0.2072959989309311,0.18646399974822997,0.19075199961662292,0.013296437761247597,0.03142400085926056,0.05215999856591225,0.03888959977775812,0.03750399872660637,0.0057399302067536314,0.020128000527620316,0.04064000025391579,0.023937600292265417,0.023648000322282314,0.004144197400898248,32,4,2048,768,151936,True,True,False,16,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.015200000256299973,0.037151999771595,0.02144480012357235,0.02195199951529503,0.005576364091933697,0.017952000722289085,0.0226879995316267,0.019934400077909233,0.019952000118792057,0.0011812499470458758,0.10063999891281128,0.13468800485134125,0.11595199964940547,0.1207519993185997,0.011974301621092394,0.16332800686359406,0.20748800039291382,0.18162400051951408,0.1767839938402176,0.01474120743720334,0.03222399950027466,0.043455999344587326,0.03829439990222454,0.03859200142323971,0.0031378131240041122,0.020959999412298203,0.03587200120091438,0.023795200139284135,0.023423999547958374,0.0031339489695198443,32,4,2048,768,151936,True,True,False,8,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.014944000169634819,0.04022400081157684,0.02162720002233982,0.022463999688625336,0.006017219317026815,0.018464000895619392,0.026528000831604004,0.021264000236988066,0.020896000787615776,0.001934095017586082,0.10156799852848053,0.1703999936580658,0.12565439902245998,0.1244799979031086,0.01641776722785409,0.1653759926557541,0.23865599930286407,0.1969360001385212,0.19223999977111816,0.02058903050274278,0.03254399821162224,0.06752000004053116,0.0443536002188921,0.041519999504089355,0.00984829071098989,0.020096000283956528,0.040031999349594116,0.026934400014579297,0.02478400059044361,0.00562071702648593,32,4,2048,768,151936,True,True,False,1,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.7531200051307678,0.8461440205574036,0.7618160009384155,0.7576479911804199,0.019464233617982506,0.2922559976577759,0.2985599935054779,0.2953856036067009,0.29576000571250916,0.001575901077689139,0.510047972202301,0.5140479803085327,0.5121696025133133,0.5123839974403381,0.0012263137313476844,,,,,,32,4,2048,768,151936,True,True,False,8192,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.39529600739479065,0.47279998660087585,0.40216960161924364,0.39825600385665894,0.0162749796240819,0.15625600516796112,0.16211199760437012,0.15959519892930984,0.15988799929618835,0.0011493418942396922,0.2635200023651123,0.2642880082130432,0.2639120012521744,0.26392000913619995,0.0001903593401384135,,,,,,32,4,2048,768,151936,True,True,False,4096,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.2531839907169342,0.32419198751449585,0.26924319565296173,0.26049599051475525,0.01657194262368116,0.10051199793815613,0.2375359982252121,0.12411200068891048,0.10311999917030334,0.039466165428540506,0.15881599485874176,0.19289599359035492,0.16896959990262986,0.1640480011701584,0.009162416086418127,,,,,,32,4,2048,768,151936,True,True,False,2048,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.15302400290966034,0.1780800074338913,0.16284480094909667,0.16113600134849548,0.00740355661356144,0.14521600306034088,0.20233599841594696,0.17807039842009545,0.1796799972653389,0.013908448560094403,0.0907519981265068,0.09750399738550186,0.09460479989647866,0.09478399902582169,0.0017965487667361475,,,,,,32,4,2048,768,151936,True,True,False,1024,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11740799993276596,0.17958399653434753,0.13262080028653145,0.12878400087356567,0.014146060532423056,0.17468799650669098,0.21161599457263947,0.1910431995987892,0.18966399878263474,0.01270903647700971,0.05926400050520897,0.07577600330114365,0.06530559975653887,0.06404799968004227,0.00479458462514625,,,,,,32,4,2048,768,151936,True,True,False,512,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11260800063610077,0.17209599912166595,0.13610880002379416,0.13809599727392197,0.017675922458993677,0.18729600310325623,0.26822400093078613,0.20815680101513861,0.2078079953789711,0.01700718593658771,0.04499199986457825,0.06537599861621857,0.0507551996037364,0.04787199944257736,0.005727123232692158,,,,,,32,4,2048,768,151936,True,True,False,256,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11257600039243698,0.23452800512313843,0.13866880126297473,0.13964799791574478,0.026590047697062115,0.1828799992799759,0.24751999974250793,0.20735519900918006,0.20670399814844131,0.01500438131586336,0.03654399886727333,0.05593600124120712,0.0408239996060729,0.03892800025641918,0.004864409450710354,,,,,,32,4,2048,768,151936,True,True,False,128,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11734399944543839,0.18726399540901184,0.13890240006148816,0.13308800011873245,0.019086167340006257,0.16991999745368958,0.2443840056657791,0.19185120090842248,0.19257599860429764,0.018017536159219673,0.03033600002527237,0.04956800118088722,0.038387199863791466,0.03750400058925152,0.00500897018702887,,,,,,32,4,2048,768,151936,True,True,False,64,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11420799791812897,0.18115200102329254,0.13938880078494548,0.1393439993262291,0.018141313962922536,0.1693439930677414,0.221343994140625,0.19187839925289155,0.19438399374485016,0.01430752121272052,0.03017600066959858,0.06019200012087822,0.03866560012102127,0.0364960003644228,0.0074199790031205266,,,,,,32,4,2048,768,151936,True,True,False,32,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11276800185441971,0.16223999857902527,0.1331360016018152,0.13305599987506866,0.01432493740801146,0.17187200486660004,0.23625600337982178,0.19287680014967917,0.1913280040025711,0.01754628831589704,0.029823999851942062,0.07574400305747986,0.03900959976017475,0.036927999928593636,0.009277465083962879,,,,,,32,4,2048,768,151936,True,True,False,16,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1130559965968132,0.19814400374889374,0.13379519879817964,0.12531199678778648,0.020074427302248836,0.16841599345207214,0.21139200031757355,0.1893615983426571,0.19092799723148346,0.012418720676762711,0.029503999277949333,0.07558400183916092,0.040144000016152856,0.03728000074625015,0.010223239196498205,,,,,,32,4,2048,768,151936,True,True,False,8,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.115167997777462,0.2640640139579773,0.13805920109152794,0.13118399679660797,0.03132849683515479,0.17103999853134155,0.2977280020713806,0.19899839907884598,0.1976960003376007,0.028928046763067948,0.0297279991209507,0.05990400165319443,0.03834720011800528,0.0363520011305809,0.0070885330713495905,,,,,,32,4,2048,768,151936,True,True,False,1,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.3940800130367279,0.46483200788497925,0.39923040121793746,0.3957759886980057,0.015108903906233569,0.16022400557994843,0.1634880006313324,0.16203359961509706,0.16228799521923065,0.0010220720912414007,0.26073598861694336,0.2627840042114258,0.26138080209493636,0.2613760083913803,0.00041640363494172775,,,,,,32,4,2048,768,151936,True,True,False,8192,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.2536959946155548,0.27161601185798645,0.25960480123758317,0.2577280104160309,0.005142017404245015,0.09849599748849869,0.10281600058078766,0.10057279989123344,0.10063999891281128,0.0008836232237268523,0.13913600146770477,0.17606399953365326,0.15875840038061143,0.15988799929618835,0.010058952112389172,,,,,,32,4,2048,768,151936,True,True,False,4096,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.15142400562763214,0.1780479997396469,0.16139679849147798,0.1602879986166954,0.0070656055731385115,0.14601600170135498,0.23343999683856964,0.17913119941949845,0.179967999458313,0.023065274309176566,0.09388799965381622,0.12108799815177917,0.10317599996924401,0.10073599964380264,0.007364345618470178,,,,,,32,4,2048,768,151936,True,True,False,2048,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12198399752378464,0.18406400084495544,0.13770400024950505,0.13232000172138214,0.01623164885687898,0.1773120015859604,0.20688000321388245,0.1870912007987499,0.18535999953746796,0.00825628058448234,0.05766399949789047,0.06739199906587601,0.06187200043350458,0.061216000467538834,0.003004312467037863,,,,,,32,4,2048,768,151936,True,True,False,1024,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11737599968910217,0.18614399433135986,0.13109439946711063,0.12771200388669968,0.01372168725934724,0.17587199807167053,0.2699519991874695,0.19926720038056372,0.19075199961662292,0.02327478982490538,0.041728001087903976,0.06224000081419945,0.05000480003654957,0.049375999718904495,0.006185850944273961,,,,,,32,4,2048,768,151936,True,True,False,512,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1159679964184761,0.1610880047082901,0.12988320142030715,0.12494400516152382,0.011865375783184065,0.1767680048942566,0.27379199862480164,0.21035519987344742,0.21275199949741364,0.023206964017550125,0.037087999284267426,0.062144000083208084,0.04439679980278015,0.04283200018107891,0.006155226392511492,,,,,,32,4,2048,768,151936,True,True,False,256,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12015999853610992,0.158720001578331,0.13573280088603495,0.1343199983239174,0.010666830836014414,0.1737920045852661,0.22127999365329742,0.20261440128087999,0.20321600139141083,0.011153965849067301,0.03587200120091438,0.04944000020623207,0.038265600241720675,0.037328001111745834,0.0030431580113575636,,,,,,32,4,2048,768,151936,True,True,False,128,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1212799996137619,0.15139199793338776,0.13183839991688728,0.13014400005340576,0.00851207547022104,0.17257599532604218,0.2250880002975464,0.1872655987739563,0.18193599581718445,0.013638284975248818,0.02969600073993206,0.0525440014898777,0.03840640028938651,0.03444799967110157,0.007598511754254174,,,,,,32,4,2048,768,151936,True,True,False,64,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11270400136709213,0.1624639928340912,0.13508000001311302,0.13180799782276154,0.014243564451606775,0.17052799463272095,0.23715199530124664,0.1953311987221241,0.1966560035943985,0.01500670718978398,0.030239999294281006,0.05270399898290634,0.03807039987295866,0.03742399998009205,0.004906165602021684,,,,,,32,4,2048,768,151936,True,True,False,32,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12319999933242798,0.17919999361038208,0.14059039913117885,0.14156799763441086,0.016217662982107223,0.1701119989156723,0.21987199783325195,0.18903039917349815,0.1870879977941513,0.014117854507841239,0.030368000268936157,0.06406400352716446,0.04045119984075427,0.03710399940609932,0.00878942205983628,,,,,,32,4,2048,768,151936,True,True,False,16,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11296000331640244,0.16761599481105804,0.13843199908733367,0.13814399391412735,0.014925286935582404,0.1711679995059967,0.21561600267887115,0.1906527981162071,0.1876479983329773,0.011803992622137974,0.0306560005992651,0.09216000139713287,0.041129599791020155,0.036847999319434166,0.013739721468154687,,,,,,32,4,2048,768,151936,True,True,False,8,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11929599940776825,0.2008959949016571,0.14535359852015972,0.13971199840307236,0.024769473061576282,0.16803200542926788,0.25123199820518494,0.19573760256171227,0.19366399943828583,0.023196011081705884,0.03049599938094616,0.08089599758386612,0.04739360017701984,0.0453919991850853,0.01286389846889463,,,,,,32,4,2048,768,151936,True,True,False,1,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
1 time_stats.emb.min time_stats.emb.max time_stats.emb.mean time_stats.emb.median time_stats.emb.std time_stats.input_layernorm.min time_stats.input_layernorm.max time_stats.input_layernorm.mean time_stats.input_layernorm.median time_stats.input_layernorm.std time_stats.attn_pre_proj.min time_stats.attn_pre_proj.max time_stats.attn_pre_proj.mean time_stats.attn_pre_proj.median time_stats.attn_pre_proj.std time_stats.attn_rope.min time_stats.attn_rope.max time_stats.attn_rope.mean time_stats.attn_rope.median time_stats.attn_rope.std time_stats.attn_post_proj.min time_stats.attn_post_proj.max time_stats.attn_post_proj.mean time_stats.attn_post_proj.median time_stats.attn_post_proj.std time_stats.post_attention_layernorm.min time_stats.post_attention_layernorm.max time_stats.post_attention_layernorm.mean time_stats.post_attention_layernorm.median time_stats.post_attention_layernorm.std n_head n_kv_head n_embd n_expanded_embd vocab_size use_gated_mlp use_qk_norm attn_output_gate num_tokens num_tensor_parallel_workers padded_n_embd padded_n_expanded_embd model_arch is_step2_mini share_expert_dim share_q_dim measurement_type profiling_precision quant_signature
2 0.029184000566601753 0.06780800223350525 0.03157280012965202 0.030736000277101994 0.005874173435341216 0.033215999603271484 0.04825599864125252 0.03443359974771738 0.0337119996547699 0.0031825678429048183 1.438431978225708 1.505568027496338 1.446228802204132 1.4429279565811157 0.014128607642643025 0.538752019405365 0.5440319776535034 0.5416463971138 0.5420799851417542 0.0016099306164432847 1.0073280334472656 1.0163840055465698 1.0098415970802308 1.0081279873847961 0.0032980457197329728 0.04022400081157684 0.041728001087903976 0.04091359991580248 0.04081599973142147 0.0004728505416767937 32 4 2048 768 151936 True True False 8192 1 2048 768 generic False CUDA_EVENT BF16 none
3 0.01360000018030405 0.06784000247716904 0.017755200061947106 0.0179840000346303 0.00837681421401443 0.01836800016462803 0.03651199862360954 0.019606399815529585 0.018719999119639397 0.0038821958848767424 0.7512000203132629 0.8208960294723511 0.7566704005002975 0.75382399559021 0.014793092586577971 0.28995200991630554 0.29337599873542786 0.29135999977588656 0.29150401055812836 0.000998381071258815 0.5149760246276855 0.5169600248336792 0.5160208016633987 0.5158880054950714 0.0005038652783291977 0.02051199972629547 0.021503999829292297 0.021067200042307378 0.021104000508785248 0.00023542855306902367 32 4 2048 768 151936 True True False 4096 1 2048 768 generic False CUDA_EVENT BF16 none
4 0.0080960001796484 0.04281599819660187 0.011092799971811474 0.011039999779313803 0.005489135752949302 0.012223999947309494 0.026335999369621277 0.013187199970707298 0.01247999956831336 0.0030236510562153375 0.3928639888763428 0.45372799038887024 0.3976895987987518 0.39528000354766846 0.012905176716136006 0.1547199934720993 0.15884800255298615 0.15712319910526276 0.1573439985513687 0.001165121945135037 0.26633599400520325 0.268095999956131 0.26719200164079665 0.2671840041875839 0.0004242740199415328 0.013024000450968742 0.013887999579310417 0.013489600038155913 0.013520000036805868 0.0002382817554057738 32 4 2048 768 151936 True True False 2048 1 2048 768 generic False CUDA_EVENT BF16 none
5 0.00825599953532219 0.04755200073122978 0.02398160002194345 0.01961600035429001 0.00874683840888523 0.018880000337958336 0.03868800029158592 0.021590400114655496 0.0208320003002882 0.004057015751746236 0.24316799640655518 0.2710399925708771 0.2521967992186546 0.25065599381923676 0.007998418528894075 0.09644799679517746 0.19120000302791595 0.10407840013504029 0.09963199868798256 0.020043722414992166 0.13600000739097595 0.18892799317836761 0.15760480016469955 0.15760000050067902 0.0112223677907762 0.009664000011980534 0.010015999898314476 0.009836799977347255 0.009824000298976898 9.016971952948177e-05 32 4 2048 768 151936 True True False 1024 1 2048 768 generic False CUDA_EVENT BF16 none
6 0.017376000061631203 0.044704001396894455 0.026318399980664254 0.027312000282108784 0.007565344034680866 0.01836800016462803 0.03014400042593479 0.021276800055056812 0.020655999891459942 0.002632977855097951 0.1438719928264618 0.17132799327373505 0.152497598528862 0.15012799948453903 0.007947150319625347 0.1430719941854477 0.19305600225925446 0.16630879789590836 0.1685439944267273 0.014628024163894684 0.08899199962615967 0.10467199981212616 0.0943599995225668 0.09374399855732918 0.003472669494074113 0.007615999784320593 0.007935999892652035 0.007769599952735007 0.0077760000713169575 7.680004540222077e-05 32 4 2048 768 151936 True True False 512 1 2048 768 generic False CUDA_EVENT BF16 none
7 0.016992000862956047 0.0544000007212162 0.02573199989274144 0.026016000658273697 0.00803323401720434 0.018432000651955605 0.02348800003528595 0.020648000109940768 0.02062400057911873 0.0013939985047930988 0.10220800340175629 0.1361600011587143 0.11850560046732425 0.11684799939393997 0.010637754898360304 0.16710400581359863 0.21110400557518005 0.19078560024499894 0.19409599900245667 0.013714352646558832 0.06265600025653839 0.0740479975938797 0.06842879951000214 0.0690080001950264 0.0031292240446560557 0.00979200005531311 0.033440001308918 0.01864320016466081 0.017280000261962414 0.006957998188876383 32 4 2048 768 151936 True True False 256 1 2048 768 generic False CUDA_EVENT BF16 none
8 0.017152000218629837 0.04396799951791763 0.025907999789342284 0.02598400041460991 0.007714554737915267 0.018400000408291817 0.03667199984192848 0.024132800102233887 0.02112000063061714 0.006120348733354326 0.10678400099277496 0.1363839954137802 0.1193264003843069 0.11583999916911125 0.009838647443214228 0.17017599940299988 0.22748799622058868 0.18853759989142418 0.18433599919080734 0.015728078443174653 0.04569600149989128 0.06652799993753433 0.05192639995366335 0.05151999928057194 0.004516605694976449 0.021856000646948814 0.026335999369621277 0.02384479995816946 0.023599999956786633 0.0011301153013314744 32 4 2048 768 151936 True True False 128 1 2048 768 generic False CUDA_EVENT BF16 none
9 0.017343999817967415 1.0683200359344482 0.05748240072280168 0.029504000209271908 0.16366824814254827 0.018688000738620758 0.3317759931087494 0.03685439983382821 0.021151999942958355 0.06767422466731164 0.10255999863147736 0.9434880018234253 0.16412640027701855 0.11956800147891045 0.17964606281728834 0.1714559942483902 2.1306240558624268 0.3011296011507511 0.1926399990916252 0.42310127734378766 0.03574400022625923 0.6859520077705383 0.08389280084520578 0.04279999993741512 0.14321647071615612 0.020479999482631683 0.1831360012292862 0.033024000097066165 0.023856000043451786 0.03470987082429836 32 4 2048 768 151936 True True False 64 1 2048 768 generic False CUDA_EVENT BF16 none
10 0.016095999628305435 0.05142400041222572 0.026363200135529043 0.02676799986511469 0.008637725852473854 0.01849599927663803 0.03577600046992302 0.022193600237369538 0.020848000422120094 0.004615266181181815 0.10540799796581268 0.15014399588108063 0.12211520001292228 0.11896000057458878 0.012772013396624768 0.17315199971199036 0.21478399634361267 0.1881632000207901 0.1873439997434616 0.011761164657572015 0.03481600061058998 0.058079998940229416 0.042200000025331974 0.03969600051641464 0.006461281521769989 0.02143999934196472 0.038816001266241074 0.02466559996828437 0.023856000043451786 0.0035418033748569927 32 4 2048 768 151936 True True False 32 1 2048 768 generic False CUDA_EVENT BF16 none
11 0.015904000028967857 0.03753599897027016 0.023127999808639287 0.02527999971061945 0.0054230027890305385 0.018400000408291817 0.03001599945127964 0.020488000102341176 0.020096000283956528 0.002585688394137697 0.10355199873447418 0.1438400000333786 0.11536479964852334 0.11124800145626068 0.011136028294919255 0.16502399742603302 0.2072959989309311 0.18646399974822997 0.19075199961662292 0.013296437761247597 0.03142400085926056 0.05215999856591225 0.03888959977775812 0.03750399872660637 0.0057399302067536314 0.020128000527620316 0.04064000025391579 0.023937600292265417 0.023648000322282314 0.004144197400898248 32 4 2048 768 151936 True True False 16 1 2048 768 generic False CUDA_EVENT BF16 none
12 0.015200000256299973 0.037151999771595 0.02144480012357235 0.02195199951529503 0.005576364091933697 0.017952000722289085 0.0226879995316267 0.019934400077909233 0.019952000118792057 0.0011812499470458758 0.10063999891281128 0.13468800485134125 0.11595199964940547 0.1207519993185997 0.011974301621092394 0.16332800686359406 0.20748800039291382 0.18162400051951408 0.1767839938402176 0.01474120743720334 0.03222399950027466 0.043455999344587326 0.03829439990222454 0.03859200142323971 0.0031378131240041122 0.020959999412298203 0.03587200120091438 0.023795200139284135 0.023423999547958374 0.0031339489695198443 32 4 2048 768 151936 True True False 8 1 2048 768 generic False CUDA_EVENT BF16 none
13 0.014944000169634819 0.04022400081157684 0.02162720002233982 0.022463999688625336 0.006017219317026815 0.018464000895619392 0.026528000831604004 0.021264000236988066 0.020896000787615776 0.001934095017586082 0.10156799852848053 0.1703999936580658 0.12565439902245998 0.1244799979031086 0.01641776722785409 0.1653759926557541 0.23865599930286407 0.1969360001385212 0.19223999977111816 0.02058903050274278 0.03254399821162224 0.06752000004053116 0.0443536002188921 0.041519999504089355 0.00984829071098989 0.020096000283956528 0.040031999349594116 0.026934400014579297 0.02478400059044361 0.00562071702648593 32 4 2048 768 151936 True True False 1 1 2048 768 generic False CUDA_EVENT BF16 none
14 0.7531200051307678 0.8461440205574036 0.7618160009384155 0.7576479911804199 0.019464233617982506 0.2922559976577759 0.2985599935054779 0.2953856036067009 0.29576000571250916 0.001575901077689139 0.510047972202301 0.5140479803085327 0.5121696025133133 0.5123839974403381 0.0012263137313476844 32 4 2048 768 151936 True True False 8192 2 2048 768 generic False CUDA_EVENT BF16 none
15 0.39529600739479065 0.47279998660087585 0.40216960161924364 0.39825600385665894 0.0162749796240819 0.15625600516796112 0.16211199760437012 0.15959519892930984 0.15988799929618835 0.0011493418942396922 0.2635200023651123 0.2642880082130432 0.2639120012521744 0.26392000913619995 0.0001903593401384135 32 4 2048 768 151936 True True False 4096 2 2048 768 generic False CUDA_EVENT BF16 none
16 0.2531839907169342 0.32419198751449585 0.26924319565296173 0.26049599051475525 0.01657194262368116 0.10051199793815613 0.2375359982252121 0.12411200068891048 0.10311999917030334 0.039466165428540506 0.15881599485874176 0.19289599359035492 0.16896959990262986 0.1640480011701584 0.009162416086418127 32 4 2048 768 151936 True True False 2048 2 2048 768 generic False CUDA_EVENT BF16 none
17 0.15302400290966034 0.1780800074338913 0.16284480094909667 0.16113600134849548 0.00740355661356144 0.14521600306034088 0.20233599841594696 0.17807039842009545 0.1796799972653389 0.013908448560094403 0.0907519981265068 0.09750399738550186 0.09460479989647866 0.09478399902582169 0.0017965487667361475 32 4 2048 768 151936 True True False 1024 2 2048 768 generic False CUDA_EVENT BF16 none
18 0.11740799993276596 0.17958399653434753 0.13262080028653145 0.12878400087356567 0.014146060532423056 0.17468799650669098 0.21161599457263947 0.1910431995987892 0.18966399878263474 0.01270903647700971 0.05926400050520897 0.07577600330114365 0.06530559975653887 0.06404799968004227 0.00479458462514625 32 4 2048 768 151936 True True False 512 2 2048 768 generic False CUDA_EVENT BF16 none
19 0.11260800063610077 0.17209599912166595 0.13610880002379416 0.13809599727392197 0.017675922458993677 0.18729600310325623 0.26822400093078613 0.20815680101513861 0.2078079953789711 0.01700718593658771 0.04499199986457825 0.06537599861621857 0.0507551996037364 0.04787199944257736 0.005727123232692158 32 4 2048 768 151936 True True False 256 2 2048 768 generic False CUDA_EVENT BF16 none
20 0.11257600039243698 0.23452800512313843 0.13866880126297473 0.13964799791574478 0.026590047697062115 0.1828799992799759 0.24751999974250793 0.20735519900918006 0.20670399814844131 0.01500438131586336 0.03654399886727333 0.05593600124120712 0.0408239996060729 0.03892800025641918 0.004864409450710354 32 4 2048 768 151936 True True False 128 2 2048 768 generic False CUDA_EVENT BF16 none
21 0.11734399944543839 0.18726399540901184 0.13890240006148816 0.13308800011873245 0.019086167340006257 0.16991999745368958 0.2443840056657791 0.19185120090842248 0.19257599860429764 0.018017536159219673 0.03033600002527237 0.04956800118088722 0.038387199863791466 0.03750400058925152 0.00500897018702887 32 4 2048 768 151936 True True False 64 2 2048 768 generic False CUDA_EVENT BF16 none
22 0.11420799791812897 0.18115200102329254 0.13938880078494548 0.1393439993262291 0.018141313962922536 0.1693439930677414 0.221343994140625 0.19187839925289155 0.19438399374485016 0.01430752121272052 0.03017600066959858 0.06019200012087822 0.03866560012102127 0.0364960003644228 0.0074199790031205266 32 4 2048 768 151936 True True False 32 2 2048 768 generic False CUDA_EVENT BF16 none
23 0.11276800185441971 0.16223999857902527 0.1331360016018152 0.13305599987506866 0.01432493740801146 0.17187200486660004 0.23625600337982178 0.19287680014967917 0.1913280040025711 0.01754628831589704 0.029823999851942062 0.07574400305747986 0.03900959976017475 0.036927999928593636 0.009277465083962879 32 4 2048 768 151936 True True False 16 2 2048 768 generic False CUDA_EVENT BF16 none
24 0.1130559965968132 0.19814400374889374 0.13379519879817964 0.12531199678778648 0.020074427302248836 0.16841599345207214 0.21139200031757355 0.1893615983426571 0.19092799723148346 0.012418720676762711 0.029503999277949333 0.07558400183916092 0.040144000016152856 0.03728000074625015 0.010223239196498205 32 4 2048 768 151936 True True False 8 2 2048 768 generic False CUDA_EVENT BF16 none
25 0.115167997777462 0.2640640139579773 0.13805920109152794 0.13118399679660797 0.03132849683515479 0.17103999853134155 0.2977280020713806 0.19899839907884598 0.1976960003376007 0.028928046763067948 0.0297279991209507 0.05990400165319443 0.03834720011800528 0.0363520011305809 0.0070885330713495905 32 4 2048 768 151936 True True False 1 2 2048 768 generic False CUDA_EVENT BF16 none
26 0.3940800130367279 0.46483200788497925 0.39923040121793746 0.3957759886980057 0.015108903906233569 0.16022400557994843 0.1634880006313324 0.16203359961509706 0.16228799521923065 0.0010220720912414007 0.26073598861694336 0.2627840042114258 0.26138080209493636 0.2613760083913803 0.00041640363494172775 32 4 2048 768 151936 True True False 8192 4 2048 768 generic False CUDA_EVENT BF16 none
27 0.2536959946155548 0.27161601185798645 0.25960480123758317 0.2577280104160309 0.005142017404245015 0.09849599748849869 0.10281600058078766 0.10057279989123344 0.10063999891281128 0.0008836232237268523 0.13913600146770477 0.17606399953365326 0.15875840038061143 0.15988799929618835 0.010058952112389172 32 4 2048 768 151936 True True False 4096 4 2048 768 generic False CUDA_EVENT BF16 none
28 0.15142400562763214 0.1780479997396469 0.16139679849147798 0.1602879986166954 0.0070656055731385115 0.14601600170135498 0.23343999683856964 0.17913119941949845 0.179967999458313 0.023065274309176566 0.09388799965381622 0.12108799815177917 0.10317599996924401 0.10073599964380264 0.007364345618470178 32 4 2048 768 151936 True True False 2048 4 2048 768 generic False CUDA_EVENT BF16 none
29 0.12198399752378464 0.18406400084495544 0.13770400024950505 0.13232000172138214 0.01623164885687898 0.1773120015859604 0.20688000321388245 0.1870912007987499 0.18535999953746796 0.00825628058448234 0.05766399949789047 0.06739199906587601 0.06187200043350458 0.061216000467538834 0.003004312467037863 32 4 2048 768 151936 True True False 1024 4 2048 768 generic False CUDA_EVENT BF16 none
30 0.11737599968910217 0.18614399433135986 0.13109439946711063 0.12771200388669968 0.01372168725934724 0.17587199807167053 0.2699519991874695 0.19926720038056372 0.19075199961662292 0.02327478982490538 0.041728001087903976 0.06224000081419945 0.05000480003654957 0.049375999718904495 0.006185850944273961 32 4 2048 768 151936 True True False 512 4 2048 768 generic False CUDA_EVENT BF16 none
31 0.1159679964184761 0.1610880047082901 0.12988320142030715 0.12494400516152382 0.011865375783184065 0.1767680048942566 0.27379199862480164 0.21035519987344742 0.21275199949741364 0.023206964017550125 0.037087999284267426 0.062144000083208084 0.04439679980278015 0.04283200018107891 0.006155226392511492 32 4 2048 768 151936 True True False 256 4 2048 768 generic False CUDA_EVENT BF16 none
32 0.12015999853610992 0.158720001578331 0.13573280088603495 0.1343199983239174 0.010666830836014414 0.1737920045852661 0.22127999365329742 0.20261440128087999 0.20321600139141083 0.011153965849067301 0.03587200120091438 0.04944000020623207 0.038265600241720675 0.037328001111745834 0.0030431580113575636 32 4 2048 768 151936 True True False 128 4 2048 768 generic False CUDA_EVENT BF16 none
33 0.1212799996137619 0.15139199793338776 0.13183839991688728 0.13014400005340576 0.00851207547022104 0.17257599532604218 0.2250880002975464 0.1872655987739563 0.18193599581718445 0.013638284975248818 0.02969600073993206 0.0525440014898777 0.03840640028938651 0.03444799967110157 0.007598511754254174 32 4 2048 768 151936 True True False 64 4 2048 768 generic False CUDA_EVENT BF16 none
34 0.11270400136709213 0.1624639928340912 0.13508000001311302 0.13180799782276154 0.014243564451606775 0.17052799463272095 0.23715199530124664 0.1953311987221241 0.1966560035943985 0.01500670718978398 0.030239999294281006 0.05270399898290634 0.03807039987295866 0.03742399998009205 0.004906165602021684 32 4 2048 768 151936 True True False 32 4 2048 768 generic False CUDA_EVENT BF16 none
35 0.12319999933242798 0.17919999361038208 0.14059039913117885 0.14156799763441086 0.016217662982107223 0.1701119989156723 0.21987199783325195 0.18903039917349815 0.1870879977941513 0.014117854507841239 0.030368000268936157 0.06406400352716446 0.04045119984075427 0.03710399940609932 0.00878942205983628 32 4 2048 768 151936 True True False 16 4 2048 768 generic False CUDA_EVENT BF16 none
36 0.11296000331640244 0.16761599481105804 0.13843199908733367 0.13814399391412735 0.014925286935582404 0.1711679995059967 0.21561600267887115 0.1906527981162071 0.1876479983329773 0.011803992622137974 0.0306560005992651 0.09216000139713287 0.041129599791020155 0.036847999319434166 0.013739721468154687 32 4 2048 768 151936 True True False 8 4 2048 768 generic False CUDA_EVENT BF16 none
37 0.11929599940776825 0.2008959949016571 0.14535359852015972 0.13971199840307236 0.024769473061576282 0.16803200542926788 0.25123199820518494 0.19573760256171227 0.19366399943828583 0.023196011081705884 0.03049599938094616 0.08089599758386612 0.04739360017701984 0.0453919991850853 0.01286389846889463 32 4 2048 768 151936 True True False 1 4 2048 768 generic False CUDA_EVENT BF16 none

View File

@@ -0,0 +1,21 @@
{
"schema": "frontier-profile-v6-code-longctx-v1",
"base": "runs/frontier-prefill-kvgrowth-fix-v0/profiles/profile-v5-kvgrowth/attention.csv",
"base_sha256": "ff32c38975e68565c85770d85b92bc310ab1d8e34fd02327bef7fb305a9ffae3",
"raw_inputs": {
"runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/raw/flashattn-code-longctx-tp1.json": "3937c623adcea3d379b82bb7ab63d3b293f917fa59fa6fd6a147581d6a252cb6",
"runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/raw/flashattn-code-longctx-tp2.json": "e48aa6e6d039bdb68759701c9976f78ad818d6778b6c40b14823a0a4e852c52d",
"runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/raw/flashattn-code-longctx-tp4.json": "759d33decc09d229d07818df8161ed41180cab575304f335ad4d5e7a917cbc93"
},
"appended_rows": 33,
"max_model_len": 147456,
"anchor_checks": [
"anchor q1ks8k/TP1: v4=1.1445ms new=1.1426ms rel_diff=0.2%",
"anchor q512s4k/TP1: v4=0.3391ms new=0.3367ms rel_diff=0.7%",
"anchor q1ks8k/TP2: v4=0.6126ms new=0.6065ms rel_diff=1.0%",
"anchor q512s4k/TP2: v4=0.2086ms new=0.2079ms rel_diff=0.3%",
"anchor q1ks8k/TP4: v4=0.3445ms new=0.3470ms rel_diff=0.7%",
"anchor q512s4k/TP4: v4=0.1536ms new=0.1510ms rel_diff=1.7%"
],
"output_sha256": "fbcf7e1f95789a6f6d771e24d1fc60958b7daf04eb0db260d27869a19d71d550"
}

View File

@@ -0,0 +1,73 @@
time_stats.moe_gating_linear.min,time_stats.moe_gating_linear.max,time_stats.moe_gating_linear.mean,time_stats.moe_gating_linear.median,time_stats.moe_gating_linear.std,time_stats.moe_gating_routing_topk.min,time_stats.moe_gating_routing_topk.max,time_stats.moe_gating_routing_topk.mean,time_stats.moe_gating_routing_topk.median,time_stats.moe_gating_routing_topk.std,time_stats.moe_shuffling.min,time_stats.moe_shuffling.max,time_stats.moe_shuffling.mean,time_stats.moe_shuffling.median,time_stats.moe_shuffling.std,time_stats.moe_grouped_gemm.min,time_stats.moe_grouped_gemm.max,time_stats.moe_grouped_gemm.mean,time_stats.moe_grouped_gemm.median,time_stats.moe_grouped_gemm.std,num_tokens,num_experts,num_experts_per_device,expert_parallel_size,routing_runtime_path,routing_assignment_policy,routing_weight_policy,routing_uses_router_logits,gating_runtime_context,gating_runtime_context_impl,router_topk,hidden_dim,expert_hidden_dim,use_gated,num_tensor_parallel_workers,total_routed_tokens,model_expansion_ratio,tokens_per_expert_avg,tokens_to_experts_ratio,expert_utilization,min_load_ratio,load_imbalance_cv,max_load_ratio,load_entropy,load_gini_coefficient,load_distribution,seed,moe_grouped_gemm_backend,measurement_type,profiling_precision,model_arch,quant_signature,router_median_nonadditivity_ratio,projection_policy
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.33926400542259216,0.405023992061615,0.36780479848384856,0.36507199704647064,0.01690507644474779,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,1.1943039894104004,1.286784052848816,1.228384006023407,1.2273280024528503,0.02832547242381263,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,64,0.375,0.5,0.5,0.3984375,0.0,1.346291201783626,4.0,5.59375,0.661865234375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,1.679744005203247,1.766144037246704,1.7095808148384095,1.7015680074691772,0.02438921262998535,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,128,0.375,1.0,1.0,0.625,0.0,1.015504800579495,5.0,6.15516433212955,0.529052734375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,2.1576640605926514,2.2921600341796875,2.2097824096679686,2.188944101333618,0.045572321842012986,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,256,0.375,2.0,2.0,0.875,0.0,0.6343057228182637,2.5,6.64370748444639,0.35369873046875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,2.422368049621582,2.5130879878997803,2.4516672134399413,2.434159994125366,0.03278900287381846,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,512,0.375,4.0,4.0,0.984375,0.0,0.4921254921257382,2.25,6.817190042344769,0.272369384765625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,2.2217600345611572,2.289599895477295,2.2571327924728393,2.263375997543335,0.021660416089449488,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,1024,0.375,8.0,8.0,1.0,0.125,0.3486861500690843,1.875,6.908192310183997,0.197662353515625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,2.18668794631958,2.318079948425293,2.2218016147613526,2.211087942123413,0.035380897213135316,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,2048,0.375,16.0,16.0,1.0,0.4375,0.2525504668006971,1.875,6.953347743053017,0.1410369873046875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,2.2291839122772217,2.3929600715637207,2.2908096313476562,2.2804640531539917,0.04479348924786221,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,4096,0.375,32.0,32.0,1.0,0.65625,0.15765965680164504,1.5625,6.98229848728205,0.08779525756835938,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,2.0678720474243164,2.1297600269317627,2.0837119817733765,2.0779199600219727,0.017880044357986735,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8192,0.375,64.0,64.0,1.0,0.625,0.12169081635504074,1.3125,6.9892029662356325,0.06879425048828125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,2.916032075881958,3.0819520950317383,2.9805248022079467,2.9656319618225098,0.05482195799019572,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,16384,0.375,128.0,128.0,1.0,0.796875,0.07935434147688751,1.1796875,6.9954297964750305,0.044734954833984375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,4.421599864959717,4.535359859466553,4.486294317245483,4.497056007385254,0.036990243787549344,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,32768,0.375,256.0,256.0,1.0,0.8203125,0.060849326483103046,1.17578125,6.9973188375859685,0.033740997314453125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,7.302591800689697,7.402751922607422,7.354758310317993,7.3464319705963135,0.032142662400335566,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,65536,0.375,512.0,512.0,1.0,0.890625,0.0412323087266341,1.08984375,6.998772433185578,0.02334284782409668,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.35280001163482666,0.39692801237106323,0.37662720382213594,0.37196800112724304,0.013401318050665304,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.4692479968070984,0.5523840188980103,0.5134752035140991,0.5100640058517456,0.02291433464135784,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.34652799367904663,0.4119040071964264,0.3789471983909607,0.38550400733947754,0.02073945105803335,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.31462401151657104,0.7456960082054138,0.38617280423641204,0.34545600414276123,0.12230201266253077,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.32521599531173706,0.419871985912323,0.36325119733810424,0.34968000650405884,0.03161798848223672,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.289792001247406,0.4663360118865967,0.4091839998960495,0.41655999422073364,0.0446001986506615,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.3761279881000519,0.4416320025920868,0.40686399936676027,0.40540799498558044,0.02257778769899645,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.7172480225563049,0.8663039803504944,0.7723807990550995,0.7591840028762817,0.04164772379451242,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,1.0195519924163818,1.2216639518737793,1.1253888130187988,1.1453600525856018,0.06548005322243594,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.7490559816360474,1.9644800424575806,1.8529024004936219,1.814303994178772,0.08042565617327288,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,3.2479360103607178,3.385279893875122,3.296070408821106,3.2800960540771484,0.04525529026442046,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,6.344799995422363,6.517856121063232,6.464438438415527,6.478623867034912,0.05116674443145098,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,1,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.2648000121116638,0.325439989566803,0.28852800130844114,0.28390398621559143,0.01933778377635077,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.7347840070724487,0.862496018409729,0.7769344031810761,0.769216001033783,0.03290485328796285,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,64,0.375,0.5,0.5,0.421875,0.0,1.346291201783626,6.0,5.652114648336087,0.636962890625,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.9198399782180786,0.9646080136299133,0.9412063956260681,0.9411839842796326,0.014939365085478117,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,128,0.375,1.0,1.0,0.5703125,0.0,1.118033988749895,5.0,6.008641773518898,0.580810546875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,1.2796800136566162,1.3484159708023071,1.3006976008415223,1.2929120063781738,0.020807998177176254,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,256,0.375,2.0,2.0,0.8828125,0.0,0.6959705453537527,3.0,6.60872850615583,0.38055419921875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,1.3630399703979492,1.4430400133132935,1.3909215927124023,1.3892319798469543,0.022335744492366926,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,512,0.375,4.0,4.0,0.984375,0.0,0.5201036555341637,3.0,6.798826509158851,0.28302001953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,1.27948796749115,1.3904000520706177,1.3176063895225525,1.309440016746521,0.038060887827312775,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,1024,0.375,8.0,8.0,1.0,0.25,0.3511282039725661,1.875,6.91002266305238,0.1970977783203125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,1.264415979385376,1.3145920038223267,1.2791999936103822,1.2753440141677856,0.014130605249568332,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,2048,0.375,16.0,16.0,1.0,0.375,0.24692938483248605,1.6875,6.955481130775285,0.13909912109375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,1.3081920146942139,1.347648024559021,1.3292255997657776,1.329967975616455,0.014558863679016933,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,4096,0.375,32.0,32.0,1.0,0.625,0.17143053326165383,1.5625,6.9786675275754035,0.09520339965820312,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,1.242751955986023,1.3112000226974487,1.2747935891151427,1.266207993030548,0.021093073517695057,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8192,0.375,64.0,64.0,1.0,0.78125,0.11000099875256815,1.296875,6.991308871213679,0.062183380126953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.7388160228729248,1.8077759742736816,1.772764801979065,1.772704005241394,0.021056644077284283,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,16384,0.375,128.0,128.0,1.0,0.78125,0.0864630150197678,1.1796875,6.994552526394139,0.048796653747558594,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,2.6563520431518555,2.7063679695129395,2.6785055875778196,2.6791679859161377,0.01639963463052944,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,32768,0.375,256.0,256.0,1.0,0.8671875,0.06127686514721937,1.16015625,6.997291583027146,0.03497934341430664,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,4.386879920959473,4.452256202697754,4.4108480453491214,4.406303882598877,0.019768161791937636,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,65536,0.375,512.0,512.0,1.0,0.884765625,0.041723768525324195,1.1171875,6.998746434318934,0.02298593521118164,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.24208000302314758,0.4028480052947998,0.3041536003351212,0.277103990316391,0.05660721484881584,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.2447039932012558,0.30502399802207947,0.26446720361709597,0.26265600323677063,0.016744548364435372,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.2337920069694519,0.2881599962711334,0.26074880361557007,0.264384001493454,0.016469850143940968,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.23369599878787994,0.28591999411582947,0.25465920120477675,0.25385600328445435,0.01593204652619194,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.2295999974012375,0.26556798815727234,0.24674240052700042,0.2497600018978119,0.010345732066199003,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.21721599996089935,0.29020801186561584,0.2394208014011383,0.2346400022506714,0.018747330357768585,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.2717759907245636,0.305184006690979,0.28813759982585907,0.28809599578380585,0.01183422600545854,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.3917759954929352,0.43772798776626587,0.41130879521369934,0.4131519943475723,0.012992473640805227,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.6176639795303345,0.7009919881820679,0.642767995595932,0.6330719888210297,0.024074084919938756,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.0820800065994263,1.1674879789352417,1.1034304022789,1.0977439880371094,0.0233067292981566,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.9809919595718384,2.0415360927581787,2.003715181350708,1.992751955986023,0.022066076434645737,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,3.790112018585205,3.8651199340820312,3.829139161109924,3.8230879306793213,0.025177464160110564,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,2,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.212351992726326,0.24383999407291412,0.22760000079870224,0.22723200172185898,0.01050568575837594,1,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.47494399547576904,0.5184000134468079,0.4920704007148743,0.49169600009918213,0.011991064701471855,8,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,64,0.375,0.5,0.5,0.3984375,0.0,1.3919410907075054,6.0,5.570159765557392,0.667236328125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.6360960006713867,0.7004479765892029,0.6608384013175964,0.6572319865226746,0.020416877242438597,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,128,0.375,1.0,1.0,0.625,0.0,1.0307764064044151,4.0,6.138251855282827,0.5382080078125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.780896008014679,0.8301439881324768,0.80346559882164,0.8030399978160858,0.016801230312128875,32,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,256,0.375,2.0,2.0,0.859375,0.0,0.6903350635742038,3.0,6.5943747091218174,0.38067626953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.8607040047645569,0.9195200204849243,0.8783008038997651,0.8751039803028107,0.01719059253115595,64,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,512,0.375,4.0,4.0,0.9765625,0.0,0.49410588440130926,2.75,6.814452474347134,0.271270751953125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.833952009677887,0.894752025604248,0.8619967997074127,0.863215982913971,0.018716378851797198,128,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,1024,0.375,8.0,8.0,1.0,0.25,0.33693529145074724,2.125,6.9186075263155535,0.1867218017578125,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.834879994392395,0.8871039748191833,0.8651552021503448,0.8638879954814911,0.015262430894400969,256,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,2048,0.375,16.0,16.0,1.0,0.375,0.25567294018677456,1.8125,6.952441049154937,0.14349365234375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.8518080115318298,0.9097599983215332,0.8810272097587586,0.8751040101051331,0.017005819633271906,512,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,4096,0.375,32.0,32.0,1.0,0.625,0.1747801353218523,1.53125,6.978069554482723,0.09820938110351562,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.8470079898834229,0.9010239839553833,0.8694015920162201,0.8716959953308105,0.016138881171190216,1024,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8192,0.375,64.0,64.0,1.0,0.65625,0.1158122428154187,1.3125,6.9901908183358845,0.06445503234863281,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,1.1698240041732788,1.2311359643936157,1.1888479948043824,1.1890720129013062,0.017978797794492758,2048,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,16384,0.375,128.0,128.0,1.0,0.78125,0.08347181893108634,1.1796875,6.994921772573154,0.046871185302734375,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.7702720165252686,1.8097599744796753,1.7919103980064393,1.7956640124320984,0.012641295676021557,4096,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,32768,0.375,256.0,256.0,1.0,0.78125,0.06866734477822484,1.20703125,6.996602562938728,0.03801727294921875,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,2.968672037124634,3.0278079509735107,2.9899007797241213,2.9824799299240112,0.01816414122631667,8192,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,65536,0.375,512.0,512.0,1.0,0.8984375,0.04399546833977376,1.126953125,6.998607314922362,0.024699926376342773,uniform_random_logits,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02502400055527687,0.06092799827456474,0.033839999698102474,0.028672000393271446,0.010315255343709818,0.019360000267624855,0.0352960005402565,0.023424000293016434,0.022064000368118286,0.0038898102289194572,0.0,0.0,0.0,0.0,0.0,0.19574399292469025,0.2512960135936737,0.21939200013875962,0.2199999988079071,0.017532156418212565,1,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8,0.375,0.0625,0.0625,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0233364439829928,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025280000641942024,0.05132799968123436,0.030641599837690593,0.027343999594449997,0.007562409232763304,0.020160000771284103,0.052960000932216644,0.024145600199699403,0.021424000151455402,0.007450198645599985,0.0,0.0,0.0,0.0,0.0,0.20483200252056122,0.24006399512290955,0.22215040028095245,0.22433599829673767,0.00969639786132892,8,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,64,0.375,0.5,0.5,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9806430689981738,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024831999093294144,0.046560000628232956,0.030371200107038022,0.02763199992477894,0.005878487205028602,0.020320000126957893,0.04560000076889992,0.02601920012384653,0.02270400058478117,0.00751129965906799,0.0,0.0,0.0,0.0,0.0,0.20559999346733093,0.24726399779319763,0.22126719802618028,0.22207999974489212,0.01328093478485499,16,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,128,0.375,1.0,1.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9103623678483975,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024288000538945198,0.049375999718904495,0.03086080001667142,0.0267359996214509,0.0070864531384997225,0.020479999482631683,0.030912000685930252,0.02274719988927245,0.021359999664127827,0.0029966813650672505,0.0,0.0,0.0,0.0,0.0,0.20003199577331543,0.2301120012998581,0.21453119963407516,0.21598400175571442,0.010402239855151332,32,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,256,0.375,2.0,2.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9610778571819444,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02393599972128868,0.04342399910092354,0.029380799923092126,0.026688000187277794,0.0057374782000526574,0.020031999796628952,0.036607999354600906,0.022487999964505435,0.020911999978125095,0.0038135203062103235,0.0,0.0,0.0,0.0,0.0,0.19551999866962433,0.22972799837589264,0.21238719969987868,0.21488000452518463,0.010706095835489097,64,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,512,0.375,4.0,4.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9952941013961014,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.025407999753952026,0.05510399863123894,0.031430399790406224,0.02798399981111288,0.007335050273982725,0.020479999482631683,0.03561599925160408,0.02275839988142252,0.021551999263465405,0.003545718365165811,0.0,0.0,0.0,0.0,0.0,0.19420799612998962,0.2903999984264374,0.2211231991648674,0.21476799994707108,0.025955008886196004,128,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,1024,0.375,8.0,8.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9273256282883522,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.0244159996509552,0.05395200103521347,0.03188959984108806,0.026031999848783016,0.00943995927387483,0.02051199972629547,0.036607999354600906,0.023247999791055917,0.02147199958562851,0.003910623837069648,0.0,0.0,0.0,0.0,0.0,0.2290560007095337,0.289247989654541,0.2543327987194061,0.24939200282096863,0.01663236753503115,256,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,2048,0.375,16.0,16.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,1.0380599882396606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.024512000381946564,0.04620800167322159,0.02884640023112297,0.026320000179111958,0.005516557583355925,0.02054399996995926,0.03846399858593941,0.023401600029319524,0.021263999864459038,0.0044742944198265374,0.0,0.0,0.0,0.0,0.0,0.30831998586654663,0.36953601241111755,0.3324000000953674,0.3288639932870865,0.018617999572156707,512,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,4096,0.375,32.0,32.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9569603278386984,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02412799932062626,0.06940799951553345,0.030817600432783365,0.026800000108778477,0.010047085187652939,0.020128000527620316,0.044096000492572784,0.024606400076299904,0.022304000332951546,0.00622857166823714,0.0,0.0,0.0,0.0,0.0,0.462911993265152,0.5497919917106628,0.4893856018781662,0.4816960096359253,0.023348152887178286,1024,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,8192,0.375,64.0,64.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.9524274993623046,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.02831999957561493,0.043487999588251114,0.031744000129401685,0.02991999965161085,0.003973415836428909,0.02070399932563305,0.029343999922275543,0.022886400017887353,0.021743999794125557,0.0026873065045088873,0.0,0.0,0.0,0.0,0.0,0.7662079930305481,0.8717759847640991,0.788454395532608,0.7744799852371216,0.03174746482604812,2048,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,16384,0.375,128.0,128.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8971818172100244,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.03830400109291077,0.06268800050020218,0.043337599746882914,0.040511999279260635,0.005823016247946116,0.023135999217629433,0.03747199848294258,0.025206399988383053,0.02393599972128868,0.003271381256231161,0.0,0.0,0.0,0.0,0.0,1.363935947418213,1.4143040180206299,1.3812703967094422,1.3798720240592957,0.014770450075530007,4096,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,32768,0.375,256.0,256.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.8113207890716184,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
0.05660799890756607,0.07932800054550171,0.06249920018017292,0.06039999984204769,0.005636461691480845,0.02956799976527691,0.03747199848294258,0.031126399897038935,0.030287999659776688,0.002157571006631541,0.0,0.0,0.0,0.0,0.0,2.5507519245147705,2.680704116821289,2.579859209060669,2.566223978996277,0.03673283558365955,8192,128,128,1,standard_fused_topk,fixed_hotset8,softmax_renorm,False,standalone_legacy,vllm020_replicated_linear,8,2048,768,True,4,65536,0.375,512.0,512.0,0.0625,0.0,3.872983346207417,16.0,3.0,0.9375,hotset8,20260716,FlashInfer CUTLASS,CUDA_EVENT,BF16,generic,none,0.883909666885606,measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
1 time_stats.moe_gating_linear.min time_stats.moe_gating_linear.max time_stats.moe_gating_linear.mean time_stats.moe_gating_linear.median time_stats.moe_gating_linear.std time_stats.moe_gating_routing_topk.min time_stats.moe_gating_routing_topk.max time_stats.moe_gating_routing_topk.mean time_stats.moe_gating_routing_topk.median time_stats.moe_gating_routing_topk.std time_stats.moe_shuffling.min time_stats.moe_shuffling.max time_stats.moe_shuffling.mean time_stats.moe_shuffling.median time_stats.moe_shuffling.std time_stats.moe_grouped_gemm.min time_stats.moe_grouped_gemm.max time_stats.moe_grouped_gemm.mean time_stats.moe_grouped_gemm.median time_stats.moe_grouped_gemm.std num_tokens num_experts num_experts_per_device expert_parallel_size routing_runtime_path routing_assignment_policy routing_weight_policy routing_uses_router_logits gating_runtime_context gating_runtime_context_impl router_topk hidden_dim expert_hidden_dim use_gated num_tensor_parallel_workers total_routed_tokens model_expansion_ratio tokens_per_expert_avg tokens_to_experts_ratio expert_utilization min_load_ratio load_imbalance_cv max_load_ratio load_entropy load_gini_coefficient load_distribution seed moe_grouped_gemm_backend measurement_type profiling_precision model_arch quant_signature router_median_nonadditivity_ratio projection_policy
2 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.33926400542259216 0.405023992061615 0.36780479848384856 0.36507199704647064 0.01690507644474779 1 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
3 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 1.1943039894104004 1.286784052848816 1.228384006023407 1.2273280024528503 0.02832547242381263 8 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 64 0.375 0.5 0.5 0.3984375 0.0 1.346291201783626 4.0 5.59375 0.661865234375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
4 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 1.679744005203247 1.766144037246704 1.7095808148384095 1.7015680074691772 0.02438921262998535 16 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 128 0.375 1.0 1.0 0.625 0.0 1.015504800579495 5.0 6.15516433212955 0.529052734375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
5 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 2.1576640605926514 2.2921600341796875 2.2097824096679686 2.188944101333618 0.045572321842012986 32 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 256 0.375 2.0 2.0 0.875 0.0 0.6343057228182637 2.5 6.64370748444639 0.35369873046875 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
6 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 2.422368049621582 2.5130879878997803 2.4516672134399413 2.434159994125366 0.03278900287381846 64 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 512 0.375 4.0 4.0 0.984375 0.0 0.4921254921257382 2.25 6.817190042344769 0.272369384765625 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
7 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 2.2217600345611572 2.289599895477295 2.2571327924728393 2.263375997543335 0.021660416089449488 128 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 1024 0.375 8.0 8.0 1.0 0.125 0.3486861500690843 1.875 6.908192310183997 0.197662353515625 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
8 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 2.18668794631958 2.318079948425293 2.2218016147613526 2.211087942123413 0.035380897213135316 256 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 2048 0.375 16.0 16.0 1.0 0.4375 0.2525504668006971 1.875 6.953347743053017 0.1410369873046875 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
9 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 2.2291839122772217 2.3929600715637207 2.2908096313476562 2.2804640531539917 0.04479348924786221 512 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 4096 0.375 32.0 32.0 1.0 0.65625 0.15765965680164504 1.5625 6.98229848728205 0.08779525756835938 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
10 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 2.0678720474243164 2.1297600269317627 2.0837119817733765 2.0779199600219727 0.017880044357986735 1024 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 8192 0.375 64.0 64.0 1.0 0.625 0.12169081635504074 1.3125 6.9892029662356325 0.06879425048828125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
11 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 2.916032075881958 3.0819520950317383 2.9805248022079467 2.9656319618225098 0.05482195799019572 2048 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 16384 0.375 128.0 128.0 1.0 0.796875 0.07935434147688751 1.1796875 6.9954297964750305 0.044734954833984375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
12 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 4.421599864959717 4.535359859466553 4.486294317245483 4.497056007385254 0.036990243787549344 4096 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 32768 0.375 256.0 256.0 1.0 0.8203125 0.060849326483103046 1.17578125 6.9973188375859685 0.033740997314453125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
13 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 7.302591800689697 7.402751922607422 7.354758310317993 7.3464319705963135 0.032142662400335566 8192 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 65536 0.375 512.0 512.0 1.0 0.890625 0.0412323087266341 1.08984375 6.998772433185578 0.02334284782409668 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
14 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.35280001163482666 0.39692801237106323 0.37662720382213594 0.37196800112724304 0.013401318050665304 1 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
15 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 0.4692479968070984 0.5523840188980103 0.5134752035140991 0.5100640058517456 0.02291433464135784 8 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 64 0.375 0.5 0.5 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
16 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 0.34652799367904663 0.4119040071964264 0.3789471983909607 0.38550400733947754 0.02073945105803335 16 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 128 0.375 1.0 1.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
17 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 0.31462401151657104 0.7456960082054138 0.38617280423641204 0.34545600414276123 0.12230201266253077 32 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 256 0.375 2.0 2.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
18 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 0.32521599531173706 0.419871985912323 0.36325119733810424 0.34968000650405884 0.03161798848223672 64 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 512 0.375 4.0 4.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
19 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 0.289792001247406 0.4663360118865967 0.4091839998960495 0.41655999422073364 0.0446001986506615 128 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 1024 0.375 8.0 8.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
20 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 0.3761279881000519 0.4416320025920868 0.40686399936676027 0.40540799498558044 0.02257778769899645 256 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 2048 0.375 16.0 16.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
21 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 0.7172480225563049 0.8663039803504944 0.7723807990550995 0.7591840028762817 0.04164772379451242 512 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 4096 0.375 32.0 32.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
22 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 1.0195519924163818 1.2216639518737793 1.1253888130187988 1.1453600525856018 0.06548005322243594 1024 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 8192 0.375 64.0 64.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
23 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 1.7490559816360474 1.9644800424575806 1.8529024004936219 1.814303994178772 0.08042565617327288 2048 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 16384 0.375 128.0 128.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
24 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 3.2479360103607178 3.385279893875122 3.296070408821106 3.2800960540771484 0.04525529026442046 4096 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 32768 0.375 256.0 256.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
25 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 6.344799995422363 6.517856121063232 6.464438438415527 6.478623867034912 0.05116674443145098 8192 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 1 65536 0.375 512.0 512.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
26 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.2648000121116638 0.325439989566803 0.28852800130844114 0.28390398621559143 0.01933778377635077 1 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
27 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 0.7347840070724487 0.862496018409729 0.7769344031810761 0.769216001033783 0.03290485328796285 8 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 64 0.375 0.5 0.5 0.421875 0.0 1.346291201783626 6.0 5.652114648336087 0.636962890625 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
28 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 0.9198399782180786 0.9646080136299133 0.9412063956260681 0.9411839842796326 0.014939365085478117 16 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 128 0.375 1.0 1.0 0.5703125 0.0 1.118033988749895 5.0 6.008641773518898 0.580810546875 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
29 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 1.2796800136566162 1.3484159708023071 1.3006976008415223 1.2929120063781738 0.020807998177176254 32 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 256 0.375 2.0 2.0 0.8828125 0.0 0.6959705453537527 3.0 6.60872850615583 0.38055419921875 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
30 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 1.3630399703979492 1.4430400133132935 1.3909215927124023 1.3892319798469543 0.022335744492366926 64 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 512 0.375 4.0 4.0 0.984375 0.0 0.5201036555341637 3.0 6.798826509158851 0.28302001953125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
31 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 1.27948796749115 1.3904000520706177 1.3176063895225525 1.309440016746521 0.038060887827312775 128 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 1024 0.375 8.0 8.0 1.0 0.25 0.3511282039725661 1.875 6.91002266305238 0.1970977783203125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
32 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 1.264415979385376 1.3145920038223267 1.2791999936103822 1.2753440141677856 0.014130605249568332 256 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 2048 0.375 16.0 16.0 1.0 0.375 0.24692938483248605 1.6875 6.955481130775285 0.13909912109375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
33 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 1.3081920146942139 1.347648024559021 1.3292255997657776 1.329967975616455 0.014558863679016933 512 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 4096 0.375 32.0 32.0 1.0 0.625 0.17143053326165383 1.5625 6.9786675275754035 0.09520339965820312 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
34 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 1.242751955986023 1.3112000226974487 1.2747935891151427 1.266207993030548 0.021093073517695057 1024 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 8192 0.375 64.0 64.0 1.0 0.78125 0.11000099875256815 1.296875 6.991308871213679 0.062183380126953125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
35 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 1.7388160228729248 1.8077759742736816 1.772764801979065 1.772704005241394 0.021056644077284283 2048 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 16384 0.375 128.0 128.0 1.0 0.78125 0.0864630150197678 1.1796875 6.994552526394139 0.048796653747558594 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
36 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 2.6563520431518555 2.7063679695129395 2.6785055875778196 2.6791679859161377 0.01639963463052944 4096 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 32768 0.375 256.0 256.0 1.0 0.8671875 0.06127686514721937 1.16015625 6.997291583027146 0.03497934341430664 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
37 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 4.386879920959473 4.452256202697754 4.4108480453491214 4.406303882598877 0.019768161791937636 8192 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 65536 0.375 512.0 512.0 1.0 0.884765625 0.041723768525324195 1.1171875 6.998746434318934 0.02298593521118164 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
38 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.24208000302314758 0.4028480052947998 0.3041536003351212 0.277103990316391 0.05660721484881584 1 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
39 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 0.2447039932012558 0.30502399802207947 0.26446720361709597 0.26265600323677063 0.016744548364435372 8 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 64 0.375 0.5 0.5 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
40 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 0.2337920069694519 0.2881599962711334 0.26074880361557007 0.264384001493454 0.016469850143940968 16 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 128 0.375 1.0 1.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
41 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 0.23369599878787994 0.28591999411582947 0.25465920120477675 0.25385600328445435 0.01593204652619194 32 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 256 0.375 2.0 2.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
42 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 0.2295999974012375 0.26556798815727234 0.24674240052700042 0.2497600018978119 0.010345732066199003 64 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 512 0.375 4.0 4.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
43 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 0.21721599996089935 0.29020801186561584 0.2394208014011383 0.2346400022506714 0.018747330357768585 128 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 1024 0.375 8.0 8.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
44 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 0.2717759907245636 0.305184006690979 0.28813759982585907 0.28809599578380585 0.01183422600545854 256 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 2048 0.375 16.0 16.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
45 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 0.3917759954929352 0.43772798776626587 0.41130879521369934 0.4131519943475723 0.012992473640805227 512 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 4096 0.375 32.0 32.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
46 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 0.6176639795303345 0.7009919881820679 0.642767995595932 0.6330719888210297 0.024074084919938756 1024 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 8192 0.375 64.0 64.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
47 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 1.0820800065994263 1.1674879789352417 1.1034304022789 1.0977439880371094 0.0233067292981566 2048 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 16384 0.375 128.0 128.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
48 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 1.9809919595718384 2.0415360927581787 2.003715181350708 1.992751955986023 0.022066076434645737 4096 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 32768 0.375 256.0 256.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
49 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 3.790112018585205 3.8651199340820312 3.829139161109924 3.8230879306793213 0.025177464160110564 8192 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 2 65536 0.375 512.0 512.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
50 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.212351992726326 0.24383999407291412 0.22760000079870224 0.22723200172185898 0.01050568575837594 1 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
51 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 0.47494399547576904 0.5184000134468079 0.4920704007148743 0.49169600009918213 0.011991064701471855 8 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 64 0.375 0.5 0.5 0.3984375 0.0 1.3919410907075054 6.0 5.570159765557392 0.667236328125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
52 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 0.6360960006713867 0.7004479765892029 0.6608384013175964 0.6572319865226746 0.020416877242438597 16 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 128 0.375 1.0 1.0 0.625 0.0 1.0307764064044151 4.0 6.138251855282827 0.5382080078125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
53 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 0.780896008014679 0.8301439881324768 0.80346559882164 0.8030399978160858 0.016801230312128875 32 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 256 0.375 2.0 2.0 0.859375 0.0 0.6903350635742038 3.0 6.5943747091218174 0.38067626953125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
54 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 0.8607040047645569 0.9195200204849243 0.8783008038997651 0.8751039803028107 0.01719059253115595 64 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 512 0.375 4.0 4.0 0.9765625 0.0 0.49410588440130926 2.75 6.814452474347134 0.271270751953125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
55 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 0.833952009677887 0.894752025604248 0.8619967997074127 0.863215982913971 0.018716378851797198 128 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 1024 0.375 8.0 8.0 1.0 0.25 0.33693529145074724 2.125 6.9186075263155535 0.1867218017578125 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
56 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 0.834879994392395 0.8871039748191833 0.8651552021503448 0.8638879954814911 0.015262430894400969 256 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 2048 0.375 16.0 16.0 1.0 0.375 0.25567294018677456 1.8125 6.952441049154937 0.14349365234375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
57 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 0.8518080115318298 0.9097599983215332 0.8810272097587586 0.8751040101051331 0.017005819633271906 512 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 4096 0.375 32.0 32.0 1.0 0.625 0.1747801353218523 1.53125 6.978069554482723 0.09820938110351562 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
58 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 0.8470079898834229 0.9010239839553833 0.8694015920162201 0.8716959953308105 0.016138881171190216 1024 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 8192 0.375 64.0 64.0 1.0 0.65625 0.1158122428154187 1.3125 6.9901908183358845 0.06445503234863281 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
59 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 1.1698240041732788 1.2311359643936157 1.1888479948043824 1.1890720129013062 0.017978797794492758 2048 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 16384 0.375 128.0 128.0 1.0 0.78125 0.08347181893108634 1.1796875 6.994921772573154 0.046871185302734375 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
60 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 1.7702720165252686 1.8097599744796753 1.7919103980064393 1.7956640124320984 0.012641295676021557 4096 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 32768 0.375 256.0 256.0 1.0 0.78125 0.06866734477822484 1.20703125 6.996602562938728 0.03801727294921875 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
61 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 2.968672037124634 3.0278079509735107 2.9899007797241213 2.9824799299240112 0.01816414122631667 8192 128 128 1 standard_fused_topk logit_topk softmax_renorm True standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 65536 0.375 512.0 512.0 1.0 0.8984375 0.04399546833977376 1.126953125 6.998607314922362 0.024699926376342773 uniform_random_logits 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
62 0.02502400055527687 0.06092799827456474 0.033839999698102474 0.028672000393271446 0.010315255343709818 0.019360000267624855 0.0352960005402565 0.023424000293016434 0.022064000368118286 0.0038898102289194572 0.0 0.0 0.0 0.0 0.0 0.19574399292469025 0.2512960135936737 0.21939200013875962 0.2199999988079071 0.017532156418212565 1 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 8 0.375 0.0625 0.0625 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0233364439829928 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
63 0.025280000641942024 0.05132799968123436 0.030641599837690593 0.027343999594449997 0.007562409232763304 0.020160000771284103 0.052960000932216644 0.024145600199699403 0.021424000151455402 0.007450198645599985 0.0 0.0 0.0 0.0 0.0 0.20483200252056122 0.24006399512290955 0.22215040028095245 0.22433599829673767 0.00969639786132892 8 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 64 0.375 0.5 0.5 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9806430689981738 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
64 0.024831999093294144 0.046560000628232956 0.030371200107038022 0.02763199992477894 0.005878487205028602 0.020320000126957893 0.04560000076889992 0.02601920012384653 0.02270400058478117 0.00751129965906799 0.0 0.0 0.0 0.0 0.0 0.20559999346733093 0.24726399779319763 0.22126719802618028 0.22207999974489212 0.01328093478485499 16 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 128 0.375 1.0 1.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9103623678483975 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
65 0.024288000538945198 0.049375999718904495 0.03086080001667142 0.0267359996214509 0.0070864531384997225 0.020479999482631683 0.030912000685930252 0.02274719988927245 0.021359999664127827 0.0029966813650672505 0.0 0.0 0.0 0.0 0.0 0.20003199577331543 0.2301120012998581 0.21453119963407516 0.21598400175571442 0.010402239855151332 32 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 256 0.375 2.0 2.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9610778571819444 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
66 0.02393599972128868 0.04342399910092354 0.029380799923092126 0.026688000187277794 0.0057374782000526574 0.020031999796628952 0.036607999354600906 0.022487999964505435 0.020911999978125095 0.0038135203062103235 0.0 0.0 0.0 0.0 0.0 0.19551999866962433 0.22972799837589264 0.21238719969987868 0.21488000452518463 0.010706095835489097 64 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 512 0.375 4.0 4.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9952941013961014 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
67 0.025407999753952026 0.05510399863123894 0.031430399790406224 0.02798399981111288 0.007335050273982725 0.020479999482631683 0.03561599925160408 0.02275839988142252 0.021551999263465405 0.003545718365165811 0.0 0.0 0.0 0.0 0.0 0.19420799612998962 0.2903999984264374 0.2211231991648674 0.21476799994707108 0.025955008886196004 128 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 1024 0.375 8.0 8.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9273256282883522 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
68 0.0244159996509552 0.05395200103521347 0.03188959984108806 0.026031999848783016 0.00943995927387483 0.02051199972629547 0.036607999354600906 0.023247999791055917 0.02147199958562851 0.003910623837069648 0.0 0.0 0.0 0.0 0.0 0.2290560007095337 0.289247989654541 0.2543327987194061 0.24939200282096863 0.01663236753503115 256 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 2048 0.375 16.0 16.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 1.0380599882396606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
69 0.024512000381946564 0.04620800167322159 0.02884640023112297 0.026320000179111958 0.005516557583355925 0.02054399996995926 0.03846399858593941 0.023401600029319524 0.021263999864459038 0.0044742944198265374 0.0 0.0 0.0 0.0 0.0 0.30831998586654663 0.36953601241111755 0.3324000000953674 0.3288639932870865 0.018617999572156707 512 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 4096 0.375 32.0 32.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9569603278386984 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
70 0.02412799932062626 0.06940799951553345 0.030817600432783365 0.026800000108778477 0.010047085187652939 0.020128000527620316 0.044096000492572784 0.024606400076299904 0.022304000332951546 0.00622857166823714 0.0 0.0 0.0 0.0 0.0 0.462911993265152 0.5497919917106628 0.4893856018781662 0.4816960096359253 0.023348152887178286 1024 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 8192 0.375 64.0 64.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.9524274993623046 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
71 0.02831999957561493 0.043487999588251114 0.031744000129401685 0.02991999965161085 0.003973415836428909 0.02070399932563305 0.029343999922275543 0.022886400017887353 0.021743999794125557 0.0026873065045088873 0.0 0.0 0.0 0.0 0.0 0.7662079930305481 0.8717759847640991 0.788454395532608 0.7744799852371216 0.03174746482604812 2048 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 16384 0.375 128.0 128.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8971818172100244 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
72 0.03830400109291077 0.06268800050020218 0.043337599746882914 0.040511999279260635 0.005823016247946116 0.023135999217629433 0.03747199848294258 0.025206399988383053 0.02393599972128868 0.003271381256231161 0.0 0.0 0.0 0.0 0.0 1.363935947418213 1.4143040180206299 1.3812703967094422 1.3798720240592957 0.014770450075530007 4096 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 32768 0.375 256.0 256.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.8113207890716184 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize
73 0.05660799890756607 0.07932800054550171 0.06249920018017292 0.06039999984204769 0.005636461691480845 0.02956799976527691 0.03747199848294258 0.031126399897038935 0.030287999659776688 0.002157571006631541 0.0 0.0 0.0 0.0 0.0 2.5507519245147705 2.680704116821289 2.579859209060669 2.566223978996277 0.03673283558365955 8192 128 128 1 standard_fused_topk fixed_hotset8 softmax_renorm False standalone_legacy vllm020_replicated_linear 8 2048 768 True 4 65536 0.375 512.0 512.0 0.0625 0.0 3.872983346207417 16.0 3.0 0.9375 hotset8 20260716 FlashInfer CUTLASS CUDA_EVENT BF16 generic none 0.883909666885606 measured_gate+topk+modular_expert;shuffling_zero_because_expert_measurement_includes_prepare_finalize

View File

@@ -0,0 +1,8 @@
3937c623adcea3d379b82bb7ab63d3b293f917fa59fa6fd6a147581d6a252cb6 runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/raw/flashattn-code-longctx-tp1.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp1-r1-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0851840004324913,
"mean_ms": 0.07839040011167527,
"median_ms": 0.07703999802470207,
"min_ms": 0.07552000135183334,
"std_ms": 0.0030805904904383677
},
"max_time": 0.043892990112304686,
"mean_time": 0.04368390693664551,
"memory_allocated_mb": 240.0849609375,
"memory_reserved_mb": 246.0,
"min_time": 0.043620254516601564,
"std_time": 8.458163192147439e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 187529.01410308387
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0854400023818016,
"mean_ms": 0.07895359992980958,
"median_ms": 0.07791999727487564,
"min_ms": 0.07718399912118912,
"std_ms": 0.0024425064759109735
},
"max_time": 0.059730175018310544,
"mean_time": 0.0595021312713623,
"memory_allocated_mb": 272.0888671875,
"memory_reserved_mb": 374.0,
"min_time": 0.05942179107666016,
"std_time": 0.00010367381308510448,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 137675.74076699864
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.09055999666452408,
"mean_ms": 0.08208959847688675,
"median_ms": 0.08087999746203423,
"min_ms": 0.07875200361013412,
"std_ms": 0.0033614630055883482
},
"max_time": 0.07555481719970703,
"mean_time": 0.07538758392333984,
"memory_allocated_mb": 304.0927734375,
"memory_reserved_mb": 534.0,
"min_time": 0.0752852783203125,
"std_time": 8.870109119325343e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 108665.10867797918
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.09888000041246414,
"mean_ms": 0.0819871999323368,
"median_ms": 0.08008000254631042,
"min_ms": 0.07788799703121185,
"std_ms": 0.005835618489111142
},
"max_time": 0.09145164489746094,
"mean_time": 0.09124225158691406,
"memory_allocated_mb": 336.0966796875,
"memory_reserved_mb": 726.0,
"min_time": 0.09113442993164063,
"std_time": 0.0001009018902177725,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 89782.96630697016
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08790399879217148,
"mean_ms": 0.07967040091753005,
"median_ms": 0.07808000221848488,
"min_ms": 0.07596799731254578,
"std_ms": 0.0036209252740976605
},
"max_time": 0.10734063720703126,
"mean_time": 0.1069560287475586,
"memory_allocated_mb": 368.1005859375,
"memory_reserved_mb": 950.0,
"min_time": 0.10689055633544922,
"std_time": 0.00013032874360676438,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 76592.22295299545
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08534400165081024,
"mean_ms": 0.07928640022873878,
"median_ms": 0.07787200063467026,
"min_ms": 0.07648000121116638,
"std_ms": 0.0028305104107121735
},
"max_time": 0.1229840316772461,
"mean_time": 0.12283342437744141,
"memory_allocated_mb": 400.1044921875,
"memory_reserved_mb": 1206.0,
"min_time": 0.12271724700927734,
"std_time": 9.625274868603512e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 66691.94514049937
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08774399757385254,
"mean_ms": 0.08081279993057251,
"median_ms": 0.07972799986600876,
"min_ms": 0.07664000242948532,
"std_ms": 0.003487270970977775
},
"max_time": 0.13109359741210938,
"mean_time": 0.13079229431152345,
"memory_allocated_mb": 416.1064453125,
"memory_reserved_mb": 1478.0,
"min_time": 0.1306565399169922,
"std_time": 0.00013138911961272913,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 62633.65929255852
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.040063999593257904,
"mean_ms": 0.019459199998527764,
"median_ms": 0.01601599995046854,
"min_ms": 0.01532800029963255,
"std_ms": 0.007496165774486326
},
"max_time": 0.009649087905883789,
"mean_time": 0.009489968109130859,
"memory_allocated_mb": 265.0458984375,
"memory_reserved_mb": 1478.0,
"min_time": 0.009443936347961425,
"std_time": 5.961646816296781e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 53951.70922728124
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.040832001715898514,
"mean_ms": 0.02942080032080412,
"median_ms": 0.027888000011444092,
"min_ms": 0.02691200003027916,
"std_ms": 0.004040048279091587
},
"max_time": 0.016906623840332032,
"mean_time": 0.01678766403198242,
"memory_allocated_mb": 168.04248046875,
"memory_reserved_mb": 1478.0,
"min_time": 0.016753759384155274,
"std_time": 4.236470233451937e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 121994.34037387963
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04867200180888176,
"mean_ms": 0.04565120078623295,
"median_ms": 0.04468800127506256,
"min_ms": 0.04416000097990036,
"std_ms": 0.0018079971851529544
},
"max_time": 0.05050300979614258,
"mean_time": 0.05035054740905761,
"memory_allocated_mb": 272.06640625,
"memory_reserved_mb": 1478.0,
"min_time": 0.05029715347290039,
"std_time": 7.24480602714254e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 81349.66173700758
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.06684800237417221,
"mean_ms": 0.06276160031557083,
"median_ms": 0.061824001371860504,
"min_ms": 0.060447998344898224,
"std_ms": 0.0024045636532566625
},
"max_time": 0.09653209686279297,
"mean_time": 0.0961898666381836,
"memory_allocated_mb": 376.09033203125,
"memory_reserved_mb": 1478.0,
"min_time": 0.09607142639160156,
"std_time": 0.0001365794879996899,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 63873.67208970714
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0326399989426136,
"mean_ms": 0.021955199912190436,
"median_ms": 0.020560000091791153,
"min_ms": 0.018559999763965607,
"std_ms": 0.00393975597463501
},
"max_time": 0.0011526399850845337,
"mean_time": 0.0011425888061523438,
"memory_allocated_mb": 34.0205078125,
"memory_reserved_mb": 1480.0,
"min_time": 0.0011403199434280396,
"std_time": 3.498447348453724e-06,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 896210.4253833097
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02783999964594841,
"mean_ms": 0.017366399988532066,
"median_ms": 0.01611199975013733,
"min_ms": 0.015424000099301338,
"std_ms": 0.003547472261377056
},
"max_time": 0.00034601598978042605,
"mean_time": 0.0003366623997688293,
"memory_allocated_mb": 17.015625,
"memory_reserved_mb": 1480.0,
"min_time": 0.0003308480083942413,
"std_time": 4.813544996936389e-06,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 1520811.3539010207
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,8 @@
f113ab5a05167f8ac4c1938c4a04fadc11d5dc2bb8c536a69db23638e6ef73d4 runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/raw/flashattn-code-longctx-tp1.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp1-r2-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08799999952316284,
"mean_ms": 0.08035840019583702,
"median_ms": 0.08003199845552444,
"min_ms": 0.07583999633789062,
"std_ms": 0.003823532942228132
},
"max_time": 0.04384675216674805,
"mean_time": 0.043662386703491214,
"memory_allocated_mb": 240.0849609375,
"memory_reserved_mb": 246.0,
"min_time": 0.04360464096069336,
"std_time": 7.18445670309503e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 187621.4430427591
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08611200004816055,
"mean_ms": 0.07973119989037514,
"median_ms": 0.07807999849319458,
"min_ms": 0.07692799717187881,
"std_ms": 0.0030488875049308785
},
"max_time": 0.05954601669311523,
"mean_time": 0.0594769702911377,
"memory_allocated_mb": 272.0888671875,
"memory_reserved_mb": 374.0,
"min_time": 0.05941872024536133,
"std_time": 4.5624842215119615e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 137733.98274828802
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.09087999910116196,
"mean_ms": 0.08214399963617325,
"median_ms": 0.08115199953317642,
"min_ms": 0.07846400141716003,
"std_ms": 0.003409163930931844
},
"max_time": 0.07549359893798828,
"mean_time": 0.07529304885864258,
"memory_allocated_mb": 304.0927734375,
"memory_reserved_mb": 534.0,
"min_time": 0.07523104095458985,
"std_time": 8.131664708395529e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 108801.5444211843
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08684799820184708,
"mean_ms": 0.08159359991550445,
"median_ms": 0.08057600259780884,
"min_ms": 0.0790719985961914,
"std_ms": 0.0025743110833498623
},
"max_time": 0.09123193359375,
"mean_time": 0.09110229187011719,
"memory_allocated_mb": 336.0966796875,
"memory_reserved_mb": 726.0,
"min_time": 0.09105142211914062,
"std_time": 5.304259171893706e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 89920.89915453696
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08508799970149994,
"mean_ms": 0.07919999957084656,
"median_ms": 0.0780319981276989,
"min_ms": 0.0764480009675026,
"std_ms": 0.002612344815356456
},
"max_time": 0.10705843353271484,
"mean_time": 0.10692193984985351,
"memory_allocated_mb": 368.1005859375,
"memory_reserved_mb": 950.0,
"min_time": 0.10688256072998047,
"std_time": 5.1132907623503757e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 76616.64211763947
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08479999750852585,
"mean_ms": 0.07948800027370453,
"median_ms": 0.07824000343680382,
"min_ms": 0.0764160007238388,
"std_ms": 0.0028062370889137406
},
"max_time": 0.12304061126708984,
"mean_time": 0.12278123931884766,
"memory_allocated_mb": 400.1044921875,
"memory_reserved_mb": 1206.0,
"min_time": 0.122716796875,
"std_time": 9.14188387039285e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 66720.29086403332
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.08329600095748901,
"mean_ms": 0.07985600009560585,
"median_ms": 0.07945600152015686,
"min_ms": 0.07705599814653397,
"std_ms": 0.0021785520776957702
},
"max_time": 0.13100553894042968,
"mean_time": 0.1307180953979492,
"memory_allocated_mb": 416.1064453125,
"memory_reserved_mb": 1478.0,
"min_time": 0.1306175994873047,
"std_time": 0.000107931256378197,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 62669.21174961153
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02659199945628643,
"mean_ms": 0.01834559990093112,
"median_ms": 0.01649599988013506,
"min_ms": 0.015135999768972397,
"std_ms": 0.00375367086613964
},
"max_time": 0.009480863571166993,
"mean_time": 0.009440905380249024,
"memory_allocated_mb": 265.0458984375,
"memory_reserved_mb": 1478.0,
"min_time": 0.009432319641113282,
"std_time": 1.4279626944428254e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 54232.08679446535
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0331839993596077,
"mean_ms": 0.028758399933576585,
"median_ms": 0.027872000820934772,
"min_ms": 0.026623999699950218,
"std_ms": 0.002088649186504863
},
"max_time": 0.01684105682373047,
"mean_time": 0.016775878524780276,
"memory_allocated_mb": 168.04248046875,
"memory_reserved_mb": 1478.0,
"min_time": 0.016756032943725584,
"std_time": 2.3830672818836446e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 122080.04468885626
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.052480001002550125,
"mean_ms": 0.045238399878144264,
"median_ms": 0.04420800134539604,
"min_ms": 0.04303999990224838,
"std_ms": 0.0027615853312914604
},
"max_time": 0.050535968780517575,
"mean_time": 0.0503309886932373,
"memory_allocated_mb": 272.06640625,
"memory_reserved_mb": 1478.0,
"min_time": 0.05029235076904297,
"std_time": 6.98791171184278e-05,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 81381.27436686649
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0740479975938797,
"mean_ms": 0.06334079951047897,
"median_ms": 0.06135999970138073,
"min_ms": 0.060095999389886856,
"std_ms": 0.004142020833679573
},
"max_time": 0.09652816009521484,
"mean_time": 0.09613609313964844,
"memory_allocated_mb": 376.09033203125,
"memory_reserved_mb": 1478.0,
"min_time": 0.09607071685791016,
"std_time": 0.0001328159156966631,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 63909.39967859056
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.028192000463604927,
"mean_ms": 0.021113600023090838,
"median_ms": 0.01923200022429228,
"min_ms": 0.018624000251293182,
"std_ms": 0.0034253398003137136
},
"max_time": 0.0011505279541015624,
"mean_time": 0.001141315186023712,
"memory_allocated_mb": 34.0205078125,
"memory_reserved_mb": 1480.0,
"min_time": 0.0011371200084686279,
"std_time": 4.555471006662272e-06,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 897210.527415803
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 4,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 32,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.021727999672293663,
"mean_ms": 0.017212800029665232,
"median_ms": 0.0161920003592968,
"min_ms": 0.015231999568641186,
"std_ms": 0.002282587014061408
},
"max_time": 0.0003445119857788086,
"mean_time": 0.0003361823946237564,
"memory_allocated_mb": 17.015625,
"memory_reserved_mb": 1480.0,
"min_time": 0.00032927998900413513,
"std_time": 4.115851563011574e-06,
"tensor_parallel_size": 1,
"throughput_tokens_per_sec": 1522982.7860944727
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,8 @@
e48aa6e6d039bdb68759701c9976f78ad818d6778b6c40b14823a0a4e852c52d runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/raw/flashattn-code-longctx-tp2.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp2-r1-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.05100800096988678,
"mean_ms": 0.04406719990074635,
"median_ms": 0.042847998440265656,
"min_ms": 0.04217600077390671,
"std_ms": 0.002656672983576728
},
"max_time": 0.022986656188964845,
"mean_time": 0.02263068161010742,
"memory_allocated_mb": 120.0849609375,
"memory_reserved_mb": 134.0,
"min_time": 0.022516607284545898,
"std_time": 0.00013840494695459716,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 361986.4457083454
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.047200001776218414,
"mean_ms": 0.043644800409674646,
"median_ms": 0.04262400045990944,
"min_ms": 0.04182400181889534,
"std_ms": 0.001927741871473188
},
"max_time": 0.030787456512451173,
"mean_time": 0.03074285774230957,
"memory_allocated_mb": 136.0888671875,
"memory_reserved_mb": 198.0,
"min_time": 0.030725727081298827,
"std_time": 1.9110324860515016e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 266468.39629114367
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.05049600079655647,
"mean_ms": 0.043852799385786054,
"median_ms": 0.04289599880576134,
"min_ms": 0.04185599833726883,
"std_ms": 0.0024573088797598033
},
"max_time": 0.03898448181152344,
"mean_time": 0.038945382690429686,
"memory_allocated_mb": 152.0927734375,
"memory_reserved_mb": 278.0,
"min_time": 0.038930206298828124,
"std_time": 1.7734743323340796e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 210345.85961362437
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.046911999583244324,
"mean_ms": 0.04412479996681214,
"median_ms": 0.04327999986708164,
"min_ms": 0.04227200150489807,
"std_ms": 0.001811858548765738
},
"max_time": 0.04724588775634766,
"mean_time": 0.04714819869995117,
"memory_allocated_mb": 168.0966796875,
"memory_reserved_mb": 374.0,
"min_time": 0.047131519317626956,
"std_time": 3.329779976561307e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 173750.01009335453
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.06195199862122536,
"mean_ms": 0.04529919996857643,
"median_ms": 0.043136000633239746,
"min_ms": 0.04182400181889534,
"std_ms": 0.005751677082163394
},
"max_time": 0.05564672088623047,
"mean_time": 0.05542207336425782,
"memory_allocated_mb": 184.1005859375,
"memory_reserved_mb": 486.0,
"min_time": 0.05533849716186524,
"std_time": 0.00011010194068839293,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 147811.14279429129
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.054687999188899994,
"mean_ms": 0.04418559968471527,
"median_ms": 0.042767999693751335,
"min_ms": 0.04182400181889534,
"std_ms": 0.0036820249064621804
},
"max_time": 0.06380697631835938,
"mean_time": 0.06362084197998047,
"memory_allocated_mb": 200.1044921875,
"memory_reserved_mb": 614.0,
"min_time": 0.06354908752441406,
"std_time": 8.872184973119366e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 128762.83533905087
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.06566400080919266,
"mean_ms": 0.05008000023663044,
"median_ms": 0.04843199998140335,
"min_ms": 0.0461760014295578,
"std_ms": 0.0055350567765421
},
"max_time": 0.06791651153564453,
"mean_time": 0.06770619888305665,
"memory_allocated_mb": 208.1064453125,
"memory_reserved_mb": 750.0,
"min_time": 0.06764147186279297,
"std_time": 9.93520482760623e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 120993.35267881997
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03859199956059456,
"mean_ms": 0.02689919974654913,
"median_ms": 0.0244159996509552,
"min_ms": 0.023711999878287315,
"std_ms": 0.004626699769228834
},
"max_time": 0.004829855918884277,
"mean_time": 0.004790303993225097,
"memory_allocated_mb": 132.5458984375,
"memory_reserved_mb": 750.0,
"min_time": 0.004775519847869873,
"std_time": 1.597276061319242e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 106882.56960813323
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0453759990632534,
"mean_ms": 0.027676799893379213,
"median_ms": 0.025200000032782555,
"min_ms": 0.024224000051617622,
"std_ms": 0.006154880946840619
},
"max_time": 0.00963871955871582,
"mean_time": 0.00959802885055542,
"memory_allocated_mb": 84.04248046875,
"memory_reserved_mb": 752.0,
"min_time": 0.009579392433166503,
"std_time": 1.6811667352984867e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 213377.14565022237
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03593600168824196,
"mean_ms": 0.02780479993671179,
"median_ms": 0.027040000073611736,
"min_ms": 0.02630399912595749,
"std_ms": 0.0027569987978884785
},
"max_time": 0.025383039474487303,
"mean_time": 0.025250255966186526,
"memory_allocated_mb": 136.06640625,
"memory_reserved_mb": 752.0,
"min_time": 0.025216863632202147,
"std_time": 4.761963064809279e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 162216.17735222535
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.041728001087903976,
"mean_ms": 0.03665280006825924,
"median_ms": 0.0352960005402565,
"min_ms": 0.034015998244285583,
"std_ms": 0.002710617869728372
},
"max_time": 0.048498847961425784,
"mean_time": 0.048172192001342776,
"memory_allocated_mb": 188.09033203125,
"memory_reserved_mb": 752.0,
"min_time": 0.04810128021240234,
"std_time": 0.00011195495368044632,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 127542.46266868527
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02191999927163124,
"mean_ms": 0.016563199926167727,
"median_ms": 0.015584000386297703,
"min_ms": 0.014879999682307243,
"std_ms": 0.002306362959594964
},
"max_time": 0.0006153280138969421,
"mean_time": 0.0006064576089382171,
"memory_allocated_mb": 17.0205078125,
"memory_reserved_mb": 752.0,
"min_time": 0.0006022400259971619,
"std_time": 4.680714919723724e-06,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 1688493.9440248988
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03843199834227562,
"mean_ms": 0.019180799927562477,
"median_ms": 0.01601599995046854,
"min_ms": 0.014911999925971031,
"std_ms": 0.006856655009795906
},
"max_time": 0.00022172799706459046,
"mean_time": 0.00020788159817457198,
"memory_allocated_mb": 8.515625,
"memory_reserved_mb": 752.0,
"min_time": 0.00019884799420833587,
"std_time": 7.012280869814824e-06,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 2462940.464648726
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,8 @@
e89bb293d5d8d6d4ec226de86ce6e4cf46daaf6eefb5b3f2809a7d079b948ecf runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/raw/flashattn-code-longctx-tp2.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp2-r2-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.047520000487565994,
"mean_ms": 0.04390720054507256,
"median_ms": 0.043088000267744064,
"min_ms": 0.041760001331567764,
"std_ms": 0.0020753894539536763
},
"max_time": 0.0226856632232666,
"mean_time": 0.022550320053100585,
"memory_allocated_mb": 120.0849609375,
"memory_reserved_mb": 134.0,
"min_time": 0.02251683235168457,
"std_time": 5.03848780842368e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 363276.440454495
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.05392000079154968,
"mean_ms": 0.04477120004594326,
"median_ms": 0.04323200136423111,
"min_ms": 0.04150399938225746,
"std_ms": 0.003602053060896233
},
"max_time": 0.03088857650756836,
"mean_time": 0.030766559982299803,
"memory_allocated_mb": 136.0888671875,
"memory_reserved_mb": 198.0,
"min_time": 0.030721696853637695,
"std_time": 5.739627345668801e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 266263.11179127306
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04835199937224388,
"mean_ms": 0.04382400028407574,
"median_ms": 0.0427200011909008,
"min_ms": 0.041600000113248825,
"std_ms": 0.002316465883417635
},
"max_time": 0.03911993789672852,
"mean_time": 0.03901147232055664,
"memory_allocated_mb": 152.0927734375,
"memory_reserved_mb": 278.0,
"min_time": 0.03894742584228516,
"std_time": 5.231496369987919e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 209989.51110295113
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04902400076389313,
"mean_ms": 0.04363839998841286,
"median_ms": 0.04273599945008755,
"min_ms": 0.04153599962592125,
"std_ms": 0.002234876899495284
},
"max_time": 0.047580448150634766,
"mean_time": 0.0472187198638916,
"memory_allocated_mb": 168.0966796875,
"memory_reserved_mb": 374.0,
"min_time": 0.04714566421508789,
"std_time": 0.00012505866815108255,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 173490.51443185066
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04848000034689903,
"mean_ms": 0.04378239996731281,
"median_ms": 0.042527999728918076,
"min_ms": 0.04163200035691261,
"std_ms": 0.002414242667964844
},
"max_time": 0.05583651351928711,
"mean_time": 0.055455712127685554,
"memory_allocated_mb": 184.1005859375,
"memory_reserved_mb": 486.0,
"min_time": 0.05535052871704101,
"std_time": 0.00014272069779462445,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 147721.48234501254
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04851200059056282,
"mean_ms": 0.04361280016601086,
"median_ms": 0.042128000408411026,
"min_ms": 0.04179200157523155,
"std_ms": 0.0023557503035821635
},
"max_time": 0.06379235076904297,
"mean_time": 0.06362125053405762,
"memory_allocated_mb": 200.1044921875,
"memory_reserved_mb": 614.0,
"min_time": 0.06355436706542969,
"std_time": 7.081883106781061e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 128762.00846782589
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.05718399956822395,
"mean_ms": 0.04485439993441105,
"median_ms": 0.042527999728918076,
"min_ms": 0.04156799986958504,
"std_ms": 0.004775190073319638
},
"max_time": 0.06783235168457032,
"mean_time": 0.06771669235229492,
"memory_allocated_mb": 208.1064453125,
"memory_reserved_mb": 750.0,
"min_time": 0.06765017700195312,
"std_time": 5.8650788028093655e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 120974.603387024
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.019807999953627586,
"mean_ms": 0.015823999978601934,
"median_ms": 0.015039999969303608,
"min_ms": 0.014303999952971935,
"std_ms": 0.001913656346272671
},
"max_time": 0.004766176223754883,
"mean_time": 0.0047575551986694335,
"memory_allocated_mb": 132.5458984375,
"memory_reserved_mb": 750.0,
"min_time": 0.004751776218414307,
"std_time": 4.190866412679079e-06,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 107618.29944573072
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02687999978661537,
"mean_ms": 0.01938559990376234,
"median_ms": 0.018383999355137348,
"min_ms": 0.018015999346971512,
"std_ms": 0.0025744710494052777
},
"max_time": 0.009582624435424805,
"mean_time": 0.009561939239501951,
"memory_allocated_mb": 84.04248046875,
"memory_reserved_mb": 752.0,
"min_time": 0.009554431915283204,
"std_time": 8.291579854680458e-06,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 214182.49464913702
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03206399828195572,
"mean_ms": 0.028105599991977214,
"median_ms": 0.02675200067460537,
"min_ms": 0.025728000327944756,
"std_ms": 0.0022390414558466644
},
"max_time": 0.02538035202026367,
"mean_time": 0.0252856897354126,
"memory_allocated_mb": 136.06640625,
"memory_reserved_mb": 752.0,
"min_time": 0.025221471786499024,
"std_time": 4.676405035080222e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 161988.85784252718
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04089599847793579,
"mean_ms": 0.03524160049855709,
"median_ms": 0.03411199897527695,
"min_ms": 0.03385600075125694,
"std_ms": 0.0022532652248236193
},
"max_time": 0.048259136199951175,
"mean_time": 0.048143408584594725,
"memory_allocated_mb": 188.09033203125,
"memory_reserved_mb": 752.0,
"min_time": 0.048105857849121095,
"std_time": 5.1879732806325464e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 127618.7162611083
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.018783999606966972,
"mean_ms": 0.015311999991536141,
"median_ms": 0.014943999703973532,
"min_ms": 0.014271999709308147,
"std_ms": 0.0012243293501672883
},
"max_time": 0.0008861759901046753,
"mean_time": 0.0006353183984756471,
"memory_allocated_mb": 17.0205078125,
"memory_reserved_mb": 752.0,
"min_time": 0.0006019840240478516,
"std_time": 8.386037831062328e-05,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 1611790.2495141604
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 2,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 16,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.019840000197291374,
"mean_ms": 0.015875199995934963,
"median_ms": 0.01497599994763732,
"min_ms": 0.014431999996304512,
"std_ms": 0.001896142444948042
},
"max_time": 0.00022230400145053863,
"mean_time": 0.00020609600096940998,
"memory_allocated_mb": 8.515625,
"memory_reserved_mb": 752.0,
"min_time": 0.00019760000705718993,
"std_time": 7.520956759601396e-06,
"tensor_parallel_size": 2,
"throughput_tokens_per_sec": 2484279.1591865686
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,8 @@
759d33decc09d229d07818df8161ed41180cab575304f335ad4d5e7a917cbc93 runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/raw/flashattn-code-longctx-tp4.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp4-r1-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.039583999663591385,
"mean_ms": 0.027286400087177753,
"median_ms": 0.025200000032782555,
"min_ms": 0.024191999807953835,
"std_ms": 0.004620118437533604
},
"max_time": 0.011496224403381348,
"mean_time": 0.011354345512390137,
"memory_allocated_mb": 60.0849609375,
"memory_reserved_mb": 62.0,
"min_time": 0.01132140827178955,
"std_time": 5.011776621543997e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 721485.8831854897
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03232000023126602,
"mean_ms": 0.026406400091946124,
"median_ms": 0.02518399991095066,
"min_ms": 0.024032000452280045,
"std_ms": 0.002792696117638337
},
"max_time": 0.015639776229858397,
"mean_time": 0.015451993656158448,
"memory_allocated_mb": 68.0888671875,
"memory_reserved_mb": 94.0,
"min_time": 0.01542249584197998,
"std_time": 6.304729308178388e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 530158.1260185833
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03488000109791756,
"mean_ms": 0.026147199980914592,
"median_ms": 0.02459200005978346,
"min_ms": 0.024224000051617622,
"std_ms": 0.003303059079404486
},
"max_time": 0.01970569610595703,
"mean_time": 0.01954985942840576,
"memory_allocated_mb": 76.0927734375,
"memory_reserved_mb": 134.0,
"min_time": 0.019525152206420898,
"std_time": 5.224891496533832e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 419031.1459783236
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03046399913728237,
"mean_ms": 0.0255103999748826,
"median_ms": 0.024656000547111034,
"min_ms": 0.024159999564290047,
"std_ms": 0.00195717586616911
},
"max_time": 0.023927040100097656,
"mean_time": 0.02367282257080078,
"memory_allocated_mb": 84.0966796875,
"memory_reserved_mb": 182.0,
"min_time": 0.023630016326904296,
"std_time": 8.715594728873713e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 346050.83426360885
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03574400022625923,
"mean_ms": 0.02678720001131296,
"median_ms": 0.024720000103116035,
"min_ms": 0.02380800060927868,
"std_ms": 0.003678231234048846
},
"max_time": 0.02779840087890625,
"mean_time": 0.027747158622741696,
"memory_allocated_mb": 92.1005859375,
"memory_reserved_mb": 238.0,
"min_time": 0.027736671447753908,
"std_time": 1.8952179343788658e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 295237.4371509809
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.042080000042915344,
"mean_ms": 0.02844479978084564,
"median_ms": 0.02527999971061945,
"min_ms": 0.024224000051617622,
"std_ms": 0.006562862750709003
},
"max_time": 0.03208835220336914,
"mean_time": 0.03186994876861572,
"memory_allocated_mb": 100.1044921875,
"memory_reserved_mb": 302.0,
"min_time": 0.03183427238464356,
"std_time": 7.444245241186317e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 257044.65543625728
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03139200061559677,
"mean_ms": 0.026396799832582474,
"median_ms": 0.025071999989449978,
"min_ms": 0.02377600036561489,
"std_ms": 0.0025962810796740263
},
"max_time": 0.033969856262207034,
"mean_time": 0.033897081375122075,
"memory_allocated_mb": 104.1064453125,
"memory_reserved_mb": 370.0,
"min_time": 0.03388313674926758,
"std_time": 2.518493598134421e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 241672.72424853416
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.022624000906944275,
"mean_ms": 0.017174400109797715,
"median_ms": 0.015536000020802021,
"min_ms": 0.014944000169634819,
"std_ms": 0.0028331860349340154
},
"max_time": 0.003192960023880005,
"mean_time": 0.003182867193222046,
"memory_allocated_mb": 66.2958984375,
"memory_reserved_mb": 372.0,
"min_time": 0.003179744005203247,
"std_time": 3.5239767128429387e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 160861.25148115202
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02985600009560585,
"mean_ms": 0.017318400088697672,
"median_ms": 0.015568000264465809,
"min_ms": 0.014655999839305878,
"std_ms": 0.004479309643844885
},
"max_time": 0.004826848030090332,
"mean_time": 0.004817302370071412,
"memory_allocated_mb": 42.04248046875,
"memory_reserved_mb": 372.0,
"min_time": 0.004811935901641846,
"std_time": 5.94674080057053e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 425134.20222979283
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03916800022125244,
"mean_ms": 0.021356799826025962,
"median_ms": 0.01935999933630228,
"min_ms": 0.017184000462293625,
"std_ms": 0.0062801287963799276
},
"max_time": 0.014635007858276367,
"mean_time": 0.014412275123596191,
"memory_allocated_mb": 68.06640625,
"memory_reserved_mb": 372.0,
"min_time": 0.014374591827392579,
"std_time": 7.569270440104603e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 284202.17938345566
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.033215999603271484,
"mean_ms": 0.023340800032019614,
"median_ms": 0.02092800009995699,
"min_ms": 0.020479999482631683,
"std_ms": 0.004304974035052475
},
"max_time": 0.02418492889404297,
"mean_time": 0.02411243553161621,
"memory_allocated_mb": 96.09033203125,
"memory_reserved_mb": 372.0,
"min_time": 0.024088096618652344,
"std_time": 2.797845886790172e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 254806.28001862322
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.04992000013589859,
"mean_ms": 0.019958400167524815,
"median_ms": 0.015552000608295202,
"min_ms": 0.014688000082969666,
"std_ms": 0.010290953685254347
},
"max_time": 0.00036675199866294863,
"mean_time": 0.0003469599992036819,
"memory_allocated_mb": 8.5205078125,
"memory_reserved_mb": 372.0,
"min_time": 0.0003364480137825012,
"std_time": 7.875187259592915e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 2951348.865431786
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.022336000576615334,
"mean_ms": 0.016252800077199935,
"median_ms": 0.014895999804139137,
"min_ms": 0.014271999709308147,
"std_ms": 0.0028271219653727385
},
"max_time": 0.00016867199540138245,
"mean_time": 0.00015103680044412614,
"memory_allocated_mb": 4.265625,
"memory_reserved_mb": 372.0,
"min_time": 0.00014329600334167482,
"std_time": 7.872199103975806e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 3389902.3184710997
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,8 @@
6ee8fdf15bef211e7d53fef0c5daf02b17429bc7d88a49cb967c2b2f6134ebe2 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/raw/flashattn-code-longctx-tp4.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.040991999208927155,
"mean_ms": 0.02782719973474741,
"median_ms": 0.025295999832451344,
"min_ms": 0.02412799932062626,
"std_ms": 0.005434033125981124
},
"max_time": 0.011621503829956055,
"mean_time": 0.011469862461090087,
"memory_allocated_mb": 60.0849609375,
"memory_reserved_mb": 62.0,
"min_time": 0.01142630386352539,
"std_time": 5.2644635131708985e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 714219.5495185945
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03811199963092804,
"mean_ms": 0.02837119996547699,
"median_ms": 0.026176000013947487,
"min_ms": 0.024159999564290047,
"std_ms": 0.004902838828525061
},
"max_time": 0.015688991546630858,
"mean_time": 0.015603910255432129,
"memory_allocated_mb": 68.0888671875,
"memory_reserved_mb": 94.0,
"min_time": 0.01557091236114502,
"std_time": 3.431861179521254e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 524996.6108429873
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.029759999364614487,
"mean_ms": 0.02612799983471632,
"median_ms": 0.025695999152958393,
"min_ms": 0.024000000208616257,
"std_ms": 0.0019206532069484194
},
"max_time": 0.020114784240722657,
"mean_time": 0.019786701011657717,
"memory_allocated_mb": 76.0927734375,
"memory_reserved_mb": 134.0,
"min_time": 0.019717824935913085,
"std_time": 0.00011854565766692264,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 414015.4538734641
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.032896000891923904,
"mean_ms": 0.026428800262510776,
"median_ms": 0.02483200002461672,
"min_ms": 0.024159999564290047,
"std_ms": 0.0028081875041272375
},
"max_time": 0.023987648010253906,
"mean_time": 0.023885836791992184,
"memory_allocated_mb": 84.0966796875,
"memory_reserved_mb": 182.0,
"min_time": 0.023849760055541992,
"std_time": 4.082290087440645e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 342964.7481618228
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03388800099492073,
"mean_ms": 0.02606080025434494,
"median_ms": 0.02440000046044588,
"min_ms": 0.023840000852942467,
"std_ms": 0.003071273491702287
},
"max_time": 0.02814064025878906,
"mean_time": 0.028014582252502435,
"memory_allocated_mb": 92.1005859375,
"memory_reserved_mb": 238.0,
"min_time": 0.027969343185424805,
"std_time": 4.739888751775852e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 292419.138224638
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02953599952161312,
"mean_ms": 0.025788800045847892,
"median_ms": 0.024800000712275505,
"min_ms": 0.024191999807953835,
"std_ms": 0.002060583463186555
},
"max_time": 0.03218783950805664,
"mean_time": 0.03215217628479004,
"memory_allocated_mb": 100.1044921875,
"memory_reserved_mb": 302.0,
"min_time": 0.03213116836547852,
"std_time": 1.9548439899050275e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 254788.35172583075
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.032735999673604965,
"mean_ms": 0.02950399983674288,
"median_ms": 0.028351999819278717,
"min_ms": 0.027904000133275986,
"std_ms": 0.0017488521169760844
},
"max_time": 0.03428476715087891,
"mean_time": 0.03422174110412597,
"memory_allocated_mb": 104.1064453125,
"memory_reserved_mb": 370.0,
"min_time": 0.034186080932617186,
"std_time": 3.324003475365458e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 239379.98873506542
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03446400165557861,
"mean_ms": 0.0248607998713851,
"median_ms": 0.023519999347627163,
"min_ms": 0.0226879995316267,
"std_ms": 0.0035075699446123015
},
"max_time": 0.003272864103317261,
"mean_time": 0.003240902423858643,
"memory_allocated_mb": 66.2958984375,
"memory_reserved_mb": 372.0,
"min_time": 0.003228480100631714,
"std_time": 1.4700871477091224e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 157980.68964705482
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03484800085425377,
"mean_ms": 0.02619840018451214,
"median_ms": 0.024639999493956566,
"min_ms": 0.02284800074994564,
"std_ms": 0.0037605668537262792
},
"max_time": 0.005165311813354492,
"mean_time": 0.004916048002243043,
"memory_allocated_mb": 42.04248046875,
"memory_reserved_mb": 372.0,
"min_time": 0.004875135898590088,
"std_time": 8.365277131314812e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 416594.79302593466
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.023615999147295952,
"mean_ms": 0.018966399878263474,
"median_ms": 0.01788800023496151,
"min_ms": 0.01679999940097332,
"std_ms": 0.0021688374822942504
},
"max_time": 0.0145830717086792,
"mean_time": 0.01451537265777588,
"memory_allocated_mb": 68.06640625,
"memory_reserved_mb": 372.0,
"min_time": 0.014502431869506836,
"std_time": 2.2952325515836057e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 282183.5922900522
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.028192000463604927,
"mean_ms": 0.021894400380551814,
"median_ms": 0.021088000386953354,
"min_ms": 0.020640000700950623,
"std_ms": 0.0021379161656161685
},
"max_time": 0.024349727630615235,
"mean_time": 0.024299632072448733,
"memory_allocated_mb": 96.09033203125,
"memory_reserved_mb": 372.0,
"min_time": 0.024284608840942384,
"std_time": 2.0842542550131525e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 252843.3344867865
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0261439997702837,
"mean_ms": 0.016019200067967178,
"median_ms": 0.01512000011280179,
"min_ms": 0.014368000440299511,
"std_ms": 0.0034013214299104646
},
"max_time": 0.0003514559864997864,
"mean_time": 0.00034397439956665037,
"memory_allocated_mb": 8.5205078125,
"memory_reserved_mb": 372.0,
"min_time": 0.0003375680148601532,
"std_time": 3.760143706773439e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 2976965.731432534
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.021023999899625778,
"mean_ms": 0.015327999833971262,
"median_ms": 0.014639999717473984,
"min_ms": 0.013856000266969204,
"std_ms": 0.0020222886267191407
},
"max_time": 0.0001605760008096695,
"mean_time": 0.0001493696004152298,
"memory_allocated_mb": 4.265625,
"memory_reserved_mb": 372.0,
"min_time": 0.00014313599467277526,
"std_time": 5.429351067501872e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 3427738.9681481416
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}

View File

@@ -0,0 +1,320 @@
{
"comparisons": [
{
"batch_spec": "q1ks8k",
"first_mean_s": 0.0011425888061523438,
"pass": true,
"relative_difference": 0.0011153009347107706,
"second_mean_s": 0.001141315186023712,
"tp": 1
},
{
"batch_spec": "q2ks66k",
"first_mean_s": 0.01678766403198242,
"pass": true,
"relative_difference": 0.0007022802901221452,
"second_mean_s": 0.016775878524780276,
"tp": 1
},
{
"batch_spec": "q4ks100k",
"first_mean_s": 0.05035054740905761,
"pass": true,
"relative_difference": 0.000388526368934946,
"second_mean_s": 0.0503309886932373,
"tp": 1
},
{
"batch_spec": "q512s128k",
"first_mean_s": 0.009489968109130859,
"pass": true,
"relative_difference": 0.005183356056904404,
"second_mean_s": 0.009440905380249024,
"tp": 1
},
{
"batch_spec": "q512s4k",
"first_mean_s": 0.0003366623997688293,
"pass": true,
"relative_difference": 0.0014267930704769689,
"second_mean_s": 0.0003361823946237564,
"tp": 1
},
{
"batch_spec": "q6ks134k",
"first_mean_s": 0.0961898666381836,
"pass": true,
"relative_difference": 0.0005591912667149224,
"second_mean_s": 0.09613609313964844,
"tp": 1
},
{
"batch_spec": "q8ks112k",
"first_mean_s": 0.1069560287475586,
"pass": true,
"relative_difference": 0.00031876960426212737,
"second_mean_s": 0.10692193984985351,
"tp": 1
},
{
"batch_spec": "q8ks128k",
"first_mean_s": 0.12283342437744141,
"pass": true,
"relative_difference": 0.0004249343895711351,
"second_mean_s": 0.12278123931884766,
"tp": 1
},
{
"batch_spec": "q8ks136k",
"first_mean_s": 0.13079229431152345,
"pass": true,
"relative_difference": 0.0005674643646600315,
"second_mean_s": 0.1307180953979492,
"tp": 1
},
{
"batch_spec": "q8ks48k",
"first_mean_s": 0.04368390693664551,
"pass": true,
"relative_difference": 0.0004927566415802605,
"second_mean_s": 0.043662386703491214,
"tp": 1
},
{
"batch_spec": "q8ks64k",
"first_mean_s": 0.0595021312713623,
"pass": true,
"relative_difference": 0.0004229478941120101,
"second_mean_s": 0.0594769702911377,
"tp": 1
},
{
"batch_spec": "q8ks80k",
"first_mean_s": 0.07538758392333984,
"pass": true,
"relative_difference": 0.0012547739275033378,
"second_mean_s": 0.07529304885864258,
"tp": 1
},
{
"batch_spec": "q8ks96k",
"first_mean_s": 0.09124225158691406,
"pass": true,
"relative_difference": 0.0015351127502189047,
"second_mean_s": 0.09110229187011719,
"tp": 1
},
{
"batch_spec": "q1ks8k",
"first_mean_s": 0.0006064576089382171,
"pass": true,
"relative_difference": 0.04648308449369336,
"second_mean_s": 0.0006353183984756471,
"tp": 2
},
{
"batch_spec": "q2ks66k",
"first_mean_s": 0.00959802885055542,
"pass": true,
"relative_difference": 0.003767189056248553,
"second_mean_s": 0.009561939239501951,
"tp": 2
},
{
"batch_spec": "q4ks100k",
"first_mean_s": 0.025250255966186526,
"pass": true,
"relative_difference": 0.001402319427652538,
"second_mean_s": 0.0252856897354126,
"tp": 2
},
{
"batch_spec": "q512s128k",
"first_mean_s": 0.004790303993225097,
"pass": true,
"relative_difference": 0.006859924072500961,
"second_mean_s": 0.0047575551986694335,
"tp": 2
},
{
"batch_spec": "q512s4k",
"first_mean_s": 0.00020788159817457198,
"pass": true,
"relative_difference": 0.008626540222728182,
"second_mean_s": 0.00020609600096940998,
"tp": 2
},
{
"batch_spec": "q6ks134k",
"first_mean_s": 0.048172192001342776,
"pass": true,
"relative_difference": 0.0005976896073522018,
"second_mean_s": 0.048143408584594725,
"tp": 2
},
{
"batch_spec": "q8ks112k",
"first_mean_s": 0.05542207336425782,
"pass": true,
"relative_difference": 0.0006067719206058191,
"second_mean_s": 0.055455712127685554,
"tp": 2
},
{
"batch_spec": "q8ks128k",
"first_mean_s": 0.06362084197998047,
"pass": true,
"relative_difference": 6.421681207537411e-06,
"second_mean_s": 0.06362125053405762,
"tp": 2
},
{
"batch_spec": "q8ks136k",
"first_mean_s": 0.06770619888305665,
"pass": true,
"relative_difference": 0.00015497334523802088,
"second_mean_s": 0.06771669235229492,
"tp": 2
},
{
"batch_spec": "q8ks48k",
"first_mean_s": 0.02263068161010742,
"pass": true,
"relative_difference": 0.003557316307676039,
"second_mean_s": 0.022550320053100585,
"tp": 2
},
{
"batch_spec": "q8ks64k",
"first_mean_s": 0.03074285774230957,
"pass": true,
"relative_difference": 0.0007706865344215391,
"second_mean_s": 0.030766559982299803,
"tp": 2
},
{
"batch_spec": "q8ks80k",
"first_mean_s": 0.038945382690429686,
"pass": true,
"relative_difference": 0.001695543775275234,
"second_mean_s": 0.03901147232055664,
"tp": 2
},
{
"batch_spec": "q8ks96k",
"first_mean_s": 0.04714819869995117,
"pass": true,
"relative_difference": 0.0014946162280953233,
"second_mean_s": 0.0472187198638916,
"tp": 2
},
{
"batch_spec": "q1ks8k",
"first_mean_s": 0.0003469599992036819,
"pass": true,
"relative_difference": 0.008642208702722183,
"second_mean_s": 0.00034397439956665037,
"tp": 4
},
{
"batch_spec": "q2ks66k",
"first_mean_s": 0.004817302370071412,
"pass": true,
"relative_difference": 0.020290162871872575,
"second_mean_s": 0.004916048002243043,
"tp": 4
},
{
"batch_spec": "q4ks100k",
"first_mean_s": 0.014412275123596191,
"pass": true,
"relative_difference": 0.007127958343441791,
"second_mean_s": 0.01451537265777588,
"tp": 4
},
{
"batch_spec": "q512s128k",
"first_mean_s": 0.003182867193222046,
"pass": true,
"relative_difference": 0.018068901625077752,
"second_mean_s": 0.003240902423858643,
"tp": 4
},
{
"batch_spec": "q512s4k",
"first_mean_s": 0.00015103680044412614,
"pass": true,
"relative_difference": 0.011099630528025208,
"second_mean_s": 0.0001493696004152298,
"tp": 4
},
{
"batch_spec": "q6ks134k",
"first_mean_s": 0.02411243553161621,
"pass": true,
"relative_difference": 0.007733466059061839,
"second_mean_s": 0.024299632072448733,
"tp": 4
},
{
"batch_spec": "q8ks112k",
"first_mean_s": 0.027747158622741696,
"pass": true,
"relative_difference": 0.009591652827304903,
"second_mean_s": 0.028014582252502435,
"tp": 4
},
{
"batch_spec": "q8ks128k",
"first_mean_s": 0.03186994876861572,
"pass": true,
"relative_difference": 0.008816561960069082,
"second_mean_s": 0.03215217628479004,
"tp": 4
},
{
"batch_spec": "q8ks136k",
"first_mean_s": 0.033897081375122075,
"pass": true,
"relative_difference": 0.009532159165047292,
"second_mean_s": 0.03422174110412597,
"tp": 4
},
{
"batch_spec": "q8ks48k",
"first_mean_s": 0.011354345512390137,
"pass": true,
"relative_difference": 0.010122318271387163,
"second_mean_s": 0.011469862461090087,
"tp": 4
},
{
"batch_spec": "q8ks64k",
"first_mean_s": 0.015451993656158448,
"pass": true,
"relative_difference": 0.00978342795663941,
"second_mean_s": 0.015603910255432129,
"tp": 4
},
{
"batch_spec": "q8ks80k",
"first_mean_s": 0.01954985942840576,
"pass": true,
"relative_difference": 0.012041804397861736,
"second_mean_s": 0.019786701011657717,
"tp": 4
},
{
"batch_spec": "q8ks96k",
"first_mean_s": 0.02367282257080078,
"pass": true,
"relative_difference": 0.008957957353947301,
"second_mean_s": 0.023885836791992184,
"tp": 4
}
],
"maximum_relative_difference": 0.04648308449369336,
"schema": "frontier-code-longctx-repeat-check-v1",
"status": "PASS",
"threshold": 0.05
}