Track simulator fidelity experiment artifacts

This commit is contained in:
2026-07-19 15:31:09 +08:00
parent e0ea7e9961
commit 4c8d581a5b
115 changed files with 42355 additions and 0 deletions

View File

@@ -0,0 +1,5 @@
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
0.010463999584317207,0.04681599885225296,0.018502399697899817,0.01104000024497509,0.014205381674858167,0.021247999742627144,0.033055998384952545,0.025439999625086786,0.024639999493956566,0.004202660707027564,0.05206400156021118,0.09040000289678574,0.0665344014763832,0.06451199948787689,0.013110543934264527,0.007327999919652939,0.011680000461637974,0.008480000123381615,0.0077760000713169575,0.0016149067494504018,0.009472000412642956,0.011103999800980091,0.010118400119245053,0.009600000455975533,0.0007061491557578713,4096,64,4,16,4,40960,1,128,0,True,FLASHINFER,False,even,[128],128,128,128,128.0,128,0.0,0.0,0.0,False,0,128,128,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT
0.010751999914646149,0.012896000407636166,0.011795200034976005,0.011359999887645245,0.0009191526000700493,0.020191999152302742,0.02755199931561947,0.02319999970495701,0.021247999742627144,0.002944486774412461,0.049215998500585556,0.06700800359249115,0.05813760012388229,0.058240000158548355,0.006895964777123649,0.007519999984651804,0.009727999567985535,0.008140799775719642,0.007807999849319458,0.0008127242879711131,0.009472000412642956,0.025248000398278236,0.01303040012717247,0.010015999898314476,0.0061233119538994085,4096,64,4,16,4,40960,1,32,0,True,FLASHINFER,False,even,[32],32,32,32,32.0,32,0.0,0.0,0.0,False,0,32,32,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT
0.010239999741315842,0.011008000001311302,0.010515199974179268,0.010432000271975994,0.0002635681936991548,0.02112000063061714,0.03843199834227562,0.025894399732351303,0.023231999948620796,0.006378760808481684,0.05417599901556969,0.06438399851322174,0.05709439888596535,0.055615998804569244,0.003697870830170538,0.007135999854654074,0.00774399982765317,0.007500800024718046,0.007552000228315592,0.0002009640969704077,0.009279999881982803,0.012736000120639801,0.01031040009111166,0.009568000212311745,0.0012940667684018582,4096,64,4,16,4,40960,1,64,0,True,FLASHINFER,False,even,[64],64,64,64,64.0,64,0.0,0.0,0.0,False,0,64,64,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT
0.010367999784648418,0.02332800067961216,0.013459200039505959,0.010847999714314938,0.004984552697426283,0.02054399996995926,0.0261439997702837,0.02255360037088394,0.022112000733613968,0.001928344367854761,0.04851200059056282,0.07968000322580338,0.058873600512743,0.056352000683546066,0.010813603870069636,0.00723200011998415,0.008352000266313553,0.007686400134116411,0.007648000027984381,0.00039524862182609345,0.008960000239312649,0.011103999800980091,0.009881599992513656,0.00940799992531538,0.0009090251198168286,4096,64,4,16,4,40960,1,96,0,True,FLASHINFER,False,even,[96],96,96,96,96.0,96,0.0,0.0,0.0,False,0,96,96,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT
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
2 0.010463999584317207 0.04681599885225296 0.018502399697899817 0.01104000024497509 0.014205381674858167 0.021247999742627144 0.033055998384952545 0.025439999625086786 0.024639999493956566 0.004202660707027564 0.05206400156021118 0.09040000289678574 0.0665344014763832 0.06451199948787689 0.013110543934264527 0.007327999919652939 0.011680000461637974 0.008480000123381615 0.0077760000713169575 0.0016149067494504018 0.009472000412642956 0.011103999800980091 0.010118400119245053 0.009600000455975533 0.0007061491557578713 4096 64 4 16 4 40960 1 128 0 True FLASHINFER False even [128] 128 128 128 128.0 128 0.0 0.0 0.0 False 0 128 128 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT
3 0.010751999914646149 0.012896000407636166 0.011795200034976005 0.011359999887645245 0.0009191526000700493 0.020191999152302742 0.02755199931561947 0.02319999970495701 0.021247999742627144 0.002944486774412461 0.049215998500585556 0.06700800359249115 0.05813760012388229 0.058240000158548355 0.006895964777123649 0.007519999984651804 0.009727999567985535 0.008140799775719642 0.007807999849319458 0.0008127242879711131 0.009472000412642956 0.025248000398278236 0.01303040012717247 0.010015999898314476 0.0061233119538994085 4096 64 4 16 4 40960 1 32 0 True FLASHINFER False even [32] 32 32 32 32.0 32 0.0 0.0 0.0 False 0 32 32 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT
4 0.010239999741315842 0.011008000001311302 0.010515199974179268 0.010432000271975994 0.0002635681936991548 0.02112000063061714 0.03843199834227562 0.025894399732351303 0.023231999948620796 0.006378760808481684 0.05417599901556969 0.06438399851322174 0.05709439888596535 0.055615998804569244 0.003697870830170538 0.007135999854654074 0.00774399982765317 0.007500800024718046 0.007552000228315592 0.0002009640969704077 0.009279999881982803 0.012736000120639801 0.01031040009111166 0.009568000212311745 0.0012940667684018582 4096 64 4 16 4 40960 1 64 0 True FLASHINFER False even [64] 64 64 64 64.0 64 0.0 0.0 0.0 False 0 64 64 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT
5 0.010367999784648418 0.02332800067961216 0.013459200039505959 0.010847999714314938 0.004984552697426283 0.02054399996995926 0.0261439997702837 0.02255360037088394 0.022112000733613968 0.001928344367854761 0.04851200059056282 0.07968000322580338 0.058873600512743 0.056352000683546066 0.010813603870069636 0.00723200011998415 0.008352000266313553 0.007686400134116411 0.007648000027984381 0.00039524862182609345 0.008960000239312649 0.011103999800980091 0.009881599992513656 0.00940799992531538 0.0009090251198168286 4096 64 4 16 4 40960 1 96 0 True FLASHINFER False even [96] 96 96 96 96.0 96 0.0 0.0 0.0 False 0 96 96 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT

View File

@@ -0,0 +1,5 @@
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
0.010463999584317207,0.04681599885225296,0.018502399697899817,0.01104000024497509,0.014205381674858167,0.021247999742627144,0.033055998384952545,0.025439999625086786,0.024639999493956566,0.004202660707027564,0.05206400156021118,0.09040000289678574,0.0665344014763832,0.06451199948787689,0.013110543934264527,0.007327999919652939,0.011680000461637974,0.008480000123381615,0.0077760000713169575,0.0016149067494504018,0.009472000412642956,0.011103999800980091,0.010118400119245053,0.009600000455975533,0.0007061491557578713,4096,64,4,16,4,40960,1,128,0,True,FLASHINFER,False,even,[128],128,128,128,128.0,128,0.0,0.0,0.0,False,0,128,128,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT,False
0.010751999914646149,0.012896000407636166,0.011795200034976005,0.011359999887645245,0.0009191526000700493,0.020191999152302742,0.02755199931561947,0.02319999970495701,0.021247999742627144,0.002944486774412461,0.049215998500585556,0.06700800359249115,0.05813760012388229,0.058240000158548355,0.006895964777123649,0.007519999984651804,0.009727999567985535,0.008140799775719642,0.007807999849319458,0.0008127242879711131,0.009472000412642956,0.025248000398278236,0.01303040012717247,0.010015999898314476,0.0061233119538994085,4096,64,4,16,4,40960,1,32,0,True,FLASHINFER,False,even,[32],32,32,32,32.0,32,0.0,0.0,0.0,False,0,32,32,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT,False
0.010239999741315842,0.011008000001311302,0.010515199974179268,0.010432000271975994,0.0002635681936991548,0.02112000063061714,0.03843199834227562,0.025894399732351303,0.023231999948620796,0.006378760808481684,0.05417599901556969,0.06438399851322174,0.05709439888596535,0.055615998804569244,0.003697870830170538,0.007135999854654074,0.00774399982765317,0.007500800024718046,0.007552000228315592,0.0002009640969704077,0.009279999881982803,0.012736000120639801,0.01031040009111166,0.009568000212311745,0.0012940667684018582,4096,64,4,16,4,40960,1,64,0,True,FLASHINFER,False,even,[64],64,64,64,64.0,64,0.0,0.0,0.0,False,0,64,64,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT,False
0.010367999784648418,0.02332800067961216,0.013459200039505959,0.010847999714314938,0.004984552697426283,0.02054399996995926,0.0261439997702837,0.02255360037088394,0.022112000733613968,0.001928344367854761,0.04851200059056282,0.07968000322580338,0.058873600512743,0.056352000683546066,0.010813603870069636,0.00723200011998415,0.008352000266313553,0.007686400134116411,0.007648000027984381,0.00039524862182609345,0.008960000239312649,0.011103999800980091,0.009881599992513656,0.00940799992531538,0.0009090251198168286,4096,64,4,16,4,40960,1,96,0,True,FLASHINFER,False,even,[96],96,96,96,96.0,96,0.0,0.0,0.0,False,0,96,96,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128,CUDA_EVENT,False
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
2 0.010463999584317207 0.04681599885225296 0.018502399697899817 0.01104000024497509 0.014205381674858167 0.021247999742627144 0.033055998384952545 0.025439999625086786 0.024639999493956566 0.004202660707027564 0.05206400156021118 0.09040000289678574 0.0665344014763832 0.06451199948787689 0.013110543934264527 0.007327999919652939 0.011680000461637974 0.008480000123381615 0.0077760000713169575 0.0016149067494504018 0.009472000412642956 0.011103999800980091 0.010118400119245053 0.009600000455975533 0.0007061491557578713 4096 64 4 16 4 40960 1 128 0 True FLASHINFER False even [128] 128 128 128 128.0 128 0.0 0.0 0.0 False 0 128 128 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT False
3 0.010751999914646149 0.012896000407636166 0.011795200034976005 0.011359999887645245 0.0009191526000700493 0.020191999152302742 0.02755199931561947 0.02319999970495701 0.021247999742627144 0.002944486774412461 0.049215998500585556 0.06700800359249115 0.05813760012388229 0.058240000158548355 0.006895964777123649 0.007519999984651804 0.009727999567985535 0.008140799775719642 0.007807999849319458 0.0008127242879711131 0.009472000412642956 0.025248000398278236 0.01303040012717247 0.010015999898314476 0.0061233119538994085 4096 64 4 16 4 40960 1 32 0 True FLASHINFER False even [32] 32 32 32 32.0 32 0.0 0.0 0.0 False 0 32 32 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT False
4 0.010239999741315842 0.011008000001311302 0.010515199974179268 0.010432000271975994 0.0002635681936991548 0.02112000063061714 0.03843199834227562 0.025894399732351303 0.023231999948620796 0.006378760808481684 0.05417599901556969 0.06438399851322174 0.05709439888596535 0.055615998804569244 0.003697870830170538 0.007135999854654074 0.00774399982765317 0.007500800024718046 0.007552000228315592 0.0002009640969704077 0.009279999881982803 0.012736000120639801 0.01031040009111166 0.009568000212311745 0.0012940667684018582 4096 64 4 16 4 40960 1 64 0 True FLASHINFER False even [64] 64 64 64 64.0 64 0.0 0.0 0.0 False 0 64 64 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT False
5 0.010367999784648418 0.02332800067961216 0.013459200039505959 0.010847999714314938 0.004984552697426283 0.02054399996995926 0.0261439997702837 0.02255360037088394 0.022112000733613968 0.001928344367854761 0.04851200059056282 0.07968000322580338 0.058873600512743 0.056352000683546066 0.010813603870069636 0.00723200011998415 0.008352000266313553 0.007686400134116411 0.007648000027984381 0.00039524862182609345 0.008960000239312649 0.011103999800980091 0.009881599992513656 0.00940799992531538 0.0009090251198168286 4096 64 4 16 4 40960 1 96 0 True FLASHINFER False even [96] 96 96 96 96.0 96 0.0 0.0 0.0 False 0 96 96 BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128 CUDA_EVENT False

View File

@@ -0,0 +1,3 @@
time_stats.attn_pre_proj.min,time_stats.attn_pre_proj.max,time_stats.attn_pre_proj.mean,time_stats.attn_pre_proj.median,time_stats.attn_pre_proj.std,time_stats.attn_rope.min,time_stats.attn_rope.max,time_stats.attn_rope.mean,time_stats.attn_rope.median,time_stats.attn_rope.std,time_stats.attn_post_proj.min,time_stats.attn_post_proj.max,time_stats.attn_post_proj.mean,time_stats.attn_post_proj.median,time_stats.attn_post_proj.std,time_stats.emb.min,time_stats.emb.max,time_stats.emb.mean,time_stats.emb.median,time_stats.emb.std,time_stats.input_layernorm.min,time_stats.input_layernorm.max,time_stats.input_layernorm.mean,time_stats.input_layernorm.median,time_stats.input_layernorm.std,time_stats.post_attention_layernorm.min,time_stats.post_attention_layernorm.max,time_stats.post_attention_layernorm.mean,time_stats.post_attention_layernorm.median,time_stats.post_attention_layernorm.std,n_head,n_kv_head,n_embd,n_expanded_embd,vocab_size,use_gated_mlp,use_qk_norm,attn_output_gate,num_tokens,num_tensor_parallel_workers,padded_n_embd,padded_n_expanded_embd,model_arch,is_step2_mini,share_expert_dim,share_q_dim,measurement_type,profiling_precision,quant_signature
0.19225600361824036,0.26678401231765747,0.22318400144577027,0.22147200256586075,0.020290217906394733,0.024639999493956566,0.04320000112056732,0.028563199937343596,0.026335999369621277,0.006067654243700026,0.09071999788284302,0.12992000579833984,0.11053120009601117,0.11033599823713303,0.011489030217015594,,,,,,,,,,,,,,,,64,4,4096,1536,151936,True,True,False,16,4,4096,1536,generic,False,,,CUDA_EVENT,BF16,method=fp8|act=dynamic|serialized=True|block=128x128
,,,,,,,,,,,,,,,0.05990400165319443,0.1345279961824417,0.08581680012866855,0.0899839997291565,0.020920650895404905,0.020160000771284103,0.0360959991812706,0.02369120018556714,0.021824000403285027,0.00439515404502141,0.01833599992096424,0.02425600029528141,0.020108799915760756,0.019407999701797962,0.001409577392533308,64,4,4096,1536,151936,True,True,False,16,1,4096,1536,generic,False,,,CUDA_EVENT,BF16,method=fp8|act=dynamic|serialized=True|block=128x128
1 time_stats.attn_pre_proj.min time_stats.attn_pre_proj.max time_stats.attn_pre_proj.mean time_stats.attn_pre_proj.median time_stats.attn_pre_proj.std time_stats.attn_rope.min time_stats.attn_rope.max time_stats.attn_rope.mean time_stats.attn_rope.median time_stats.attn_rope.std time_stats.attn_post_proj.min time_stats.attn_post_proj.max time_stats.attn_post_proj.mean time_stats.attn_post_proj.median time_stats.attn_post_proj.std time_stats.emb.min time_stats.emb.max time_stats.emb.mean time_stats.emb.median time_stats.emb.std time_stats.input_layernorm.min time_stats.input_layernorm.max time_stats.input_layernorm.mean time_stats.input_layernorm.median time_stats.input_layernorm.std time_stats.post_attention_layernorm.min time_stats.post_attention_layernorm.max time_stats.post_attention_layernorm.mean time_stats.post_attention_layernorm.median time_stats.post_attention_layernorm.std n_head n_kv_head n_embd n_expanded_embd vocab_size use_gated_mlp use_qk_norm attn_output_gate num_tokens num_tensor_parallel_workers padded_n_embd padded_n_expanded_embd model_arch is_step2_mini share_expert_dim share_q_dim measurement_type profiling_precision quant_signature
2 0.19225600361824036 0.26678401231765747 0.22318400144577027 0.22147200256586075 0.020290217906394733 0.024639999493956566 0.04320000112056732 0.028563199937343596 0.026335999369621277 0.006067654243700026 0.09071999788284302 0.12992000579833984 0.11053120009601117 0.11033599823713303 0.011489030217015594 64 4 4096 1536 151936 True True False 16 4 4096 1536 generic False CUDA_EVENT BF16 method=fp8|act=dynamic|serialized=True|block=128x128
3 0.05990400165319443 0.1345279961824417 0.08581680012866855 0.0899839997291565 0.020920650895404905 0.020160000771284103 0.0360959991812706 0.02369120018556714 0.021824000403285027 0.00439515404502141 0.01833599992096424 0.02425600029528141 0.020108799915760756 0.019407999701797962 0.001409577392533308 64 4 4096 1536 151936 True True False 16 1 4096 1536 generic False CUDA_EVENT BF16 method=fp8|act=dynamic|serialized=True|block=128x128

View File

@@ -0,0 +1,2 @@
time_stats.moe_gating_linear.min,time_stats.moe_gating_linear.max,time_stats.moe_gating_linear.mean,time_stats.moe_gating_linear.median,time_stats.moe_gating_linear.std,time_stats.moe_gating_routing_topk.min,time_stats.moe_gating_routing_topk.max,time_stats.moe_gating_routing_topk.mean,time_stats.moe_gating_routing_topk.median,time_stats.moe_gating_routing_topk.std,time_stats.moe_shuffling.min,time_stats.moe_shuffling.max,time_stats.moe_shuffling.mean,time_stats.moe_shuffling.median,time_stats.moe_shuffling.std,time_stats.moe_grouped_gemm.min,time_stats.moe_grouped_gemm.max,time_stats.moe_grouped_gemm.mean,time_stats.moe_grouped_gemm.median,time_stats.moe_grouped_gemm.std,num_tokens,num_experts,num_experts_per_device,expert_parallel_size,routing_runtime_path,routing_assignment_policy,routing_weight_policy,routing_uses_router_logits,gating_runtime_context,gating_runtime_context_impl,router_topk,hidden_dim,expert_hidden_dim,use_gated,num_tensor_parallel_workers,total_routed_tokens,model_expansion_ratio,tokens_per_expert_avg,tokens_to_experts_ratio,expert_utilization,min_load_ratio,load_imbalance_cv,max_load_ratio,load_entropy,load_gini_coefficient,load_distribution,seed,moe_grouped_gemm_backend,measurement_type,profiling_precision,model_arch,quant_signature
0.03097599931061268,0.049056001007556915,0.03467839974910021,0.03254400007426739,0.005093522706269737,0.05193600058555603,0.08419200032949448,0.06054240055382252,0.05641600117087364,0.009051489911083033,0.025919999927282333,0.04064000025391579,0.030527999717742206,0.030608000233769417,0.0040231266205605675,0.29603201150894165,0.3494400084018707,0.3075023889541626,0.30137598514556885,0.014090820215642452,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.609375,0.0,1.0231690964840563,4.0,6.122626857503489,0.5433349609375,uniform,0,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
1 time_stats.moe_gating_linear.min time_stats.moe_gating_linear.max time_stats.moe_gating_linear.mean time_stats.moe_gating_linear.median time_stats.moe_gating_linear.std time_stats.moe_gating_routing_topk.min time_stats.moe_gating_routing_topk.max time_stats.moe_gating_routing_topk.mean time_stats.moe_gating_routing_topk.median time_stats.moe_gating_routing_topk.std time_stats.moe_shuffling.min time_stats.moe_shuffling.max time_stats.moe_shuffling.mean time_stats.moe_shuffling.median time_stats.moe_shuffling.std time_stats.moe_grouped_gemm.min time_stats.moe_grouped_gemm.max time_stats.moe_grouped_gemm.mean time_stats.moe_grouped_gemm.median time_stats.moe_grouped_gemm.std num_tokens num_experts num_experts_per_device expert_parallel_size routing_runtime_path routing_assignment_policy routing_weight_policy routing_uses_router_logits gating_runtime_context gating_runtime_context_impl router_topk hidden_dim expert_hidden_dim use_gated num_tensor_parallel_workers total_routed_tokens model_expansion_ratio tokens_per_expert_avg tokens_to_experts_ratio expert_utilization min_load_ratio load_imbalance_cv max_load_ratio load_entropy load_gini_coefficient load_distribution seed moe_grouped_gemm_backend measurement_type profiling_precision model_arch quant_signature
2 0.03097599931061268 0.049056001007556915 0.03467839974910021 0.03254400007426739 0.005093522706269737 0.05193600058555603 0.08419200032949448 0.06054240055382252 0.05641600117087364 0.009051489911083033 0.025919999927282333 0.04064000025391579 0.030527999717742206 0.030608000233769417 0.0040231266205605675 0.29603201150894165 0.3494400084018707 0.3075023889541626 0.30137598514556885 0.014090820215642452 16 128 128 1 standard_fused_topk logit_topk softmax_renorm True prefill_hot ffn_like_prefix_20x 8 4096 1536 True 4 128 0.375 1.0 1.0 0.609375 0.0 1.0231690964840563 4.0 6.122626857503489 0.5433349609375 uniform 0 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128

View File

@@ -0,0 +1,65 @@
attention_backend: FLASHINFER
batch_size_list:
- 1
block_shape: null
block_size: 16
decode_kv_cache_size_list: null
device: h20
disable_ray: true
disable_replicated: false
enable_chunked_prefill_grid_search: false
enable_mixed_prefill: false
enable_true_mixed: false
fixed_chunked_prefill_size: 128
max_batch_size: 1
max_mixed_batch_size: 8
max_model_len: 40960
max_pipeline_parallel_size: 1
max_seq_len: 128
min_batch_size: 1
mixed_batch_size_list: null
mixed_batch_size_max: 32
mixed_batch_size_min: 2
mixed_kv_cache_size_list:
- 0
mixed_mode: both
mixed_num_samples: 3
mixed_profile_strategy: default
mixed_shapes_per_point: 2
mixed_total_tokens_list: null
mixed_total_tokens_max: 1055
mixed_total_tokens_min: 1025
models:
- Qwen3-235B-A22B-FP8
num_gpus: 1
num_tensor_parallel_workers:
- 4
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles
precision: null
profile_method: cuda_event
profile_only_decode: false
profile_only_prefill: true
skip_confirmation: true
true_mixed_decode_batch_sizes:
- 1
- 2
- 4
- 8
true_mixed_decode_kv_cache_sizes:
- 128
- 256
- 512
- 1024
- 2048
true_mixed_prefill_batch_sizes:
- 1
- 2
- 4
true_mixed_prefill_chunk_sizes:
- 64
- 128
- 256
- 512
- 1024
true_mixed_prefill_kv_cache_size: 0
use_fp8: null

View File

@@ -0,0 +1,23 @@
attn_tp: null
block_shape: null
device: h20
disable_ray: true
disable_replicated: false
extra_num_tokens: null
ffn_tp: null
include_target_embedded_mtp: false
is_moe: true
max_tokens: 16
models:
- Qwen3-235B-A22B-FP8
num_gpus: 1
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles
precision: null
profile_method: cuda_event
ray_enable_datasets_serializers: false
skip_confirmation: true
use_fp8: null

View File

@@ -0,0 +1,27 @@
block_shape: null
device: h20
disable_ray: true
disable_replicated: false
enable_load_imbalance: true
expert_parallel_sizes:
- 1
extra_num_tokens: null
gating_runtime_context: prefill_hot
load_distributions:
- uniform
max_tokens: 16
models:
- Qwen3-235B-A22B-FP8
num_gpus: 1
num_samples_per_distribution: 1
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null