91 KiB
91 KiB
| 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 | 0.014720000326633453 | 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 | ||||||||||
| 53 | 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 | ||||||||||
| 54 | 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 | ||||||||||
| 55 | 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 | ||||||||||
| 56 | 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 | ||||||||||
| 57 | 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 | ||||||||||
| 58 | 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 | ||||||||||
| 59 | 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 | ||||||||||
| 60 | 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 | ||||||||||
| 61 | 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 | ||||||||||
| 62 | 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 | ||||||||||
| 63 | 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 | ||||||||||
| 64 | 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 | ||||||||||
| 65 | 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 | ||||||||||
| 66 | 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 | ||||||||||
| 67 | 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 | ||||||||||
| 68 | 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 | ||||||||||
| 69 | 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 | ||||||||||
| 70 | 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 | ||||||||||
| 71 | 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 | ||||||||||
| 72 | 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 | ||||||||||
| 73 | 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 | ||||||||||
| 74 | 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 | ||||||||||
| 75 | 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 | ||||||||||
| 76 | 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 | ||||||||||
| 77 | 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 | ||||||||||
| 78 | 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 | ||||||||||
| 79 | 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 | ||||||||||
| 80 | 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 | ||||||||||
| 81 | 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 | ||||||||||
| 82 | 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 | ||||||||||
| 83 | 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 | ||||||||||
| 84 | 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 | ||||||||||
| 85 | 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 | ||||||||||
| 86 | 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 | ||||||||||
| 87 | 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 | ||||||||||
| 88 | 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 | ||||||||||
| 89 | 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 | ||||||||||
| 90 | 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 | ||||||||||
| 91 | 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 | ||||||||||
| 92 | 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 | ||||||||||
| 93 | 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 | ||||||||||
| 94 | 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 | ||||||||||
| 95 | 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 | ||||||||||
| 96 | 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 | ||||||||||
| 97 | 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 | ||||||||||
| 98 | 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 | ||||||||||
| 99 | 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 | ||||||||||
| 100 | 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 | ||||||||||
| 101 | 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 | ||||||||||
| 102 | 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 | ||||||||||
| 103 | 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 | ||||||||||
| 104 | 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 | ||||||||||
| 105 | 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 | ||||||||||
| 106 | 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 | ||||||||||
| 107 | 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 | ||||||||||
| 108 | 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 | ||||||||||
| 109 | 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 | ||||||||||
| 110 | 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 | ||||||||||
| 111 | 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 | ||||||||||
| 112 | 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 | ||||||||||
| 113 | 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 | ||||||||||
| 114 | 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 | ||||||||||
| 115 | 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 | ||||||||||
| 116 | 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 | ||||||||||
| 117 | 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 | ||||||||||
| 118 | 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 | ||||||||||
| 119 | 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 | ||||||||||
| 120 | 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 | ||||||||||
| 121 | 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 | ||||||||||
| 122 | 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 | ||||||||||
| 123 | 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 | ||||||||||
| 124 | 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 | ||||||||||
| 125 | 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 | ||||||||||
| 126 | 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 | ||||||||||
| 127 | 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 | ||||||||||
| 128 | 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 | ||||||||||
| 129 | 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 | ||||||||||
| 130 | 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 | ||||||||||
| 131 | 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 | ||||||||||
| 132 | 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 | ||||||||||
| 133 | 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 | ||||||||||
| 134 | 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 | ||||||||||
| 135 | 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 | ||||||||||
| 136 | 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 | ||||||||||
| 137 | 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 | ||||||||||
| 138 | 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 | ||||||||||
| 139 | 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 | ||||||||||
| 140 | 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 | ||||||||||
| 141 | 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 | ||||||||||
| 142 | 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 | ||||||||||
| 143 | 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 | ||||||||||
| 144 | 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 | ||||||||||
| 145 | 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 | ||||||||||
| 146 | 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 | ||||||||||
| 147 | 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 | ||||||||||
| 148 | 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 | ||||||||||
| 149 | 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 | ||||||||||
| 150 | 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 | ||||||||||
| 151 | 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 |