gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Track simulator fidelity experiment artifacts

Browse Source
This commit is contained in:
Gahow Wang
2026-07-19 15:31:09 +08:00
parent e0ea7e9961
commit 4c8d581a5b
115 changed files with 42355 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/aligned/compute/h20/Qwen3-235B-A22B-FP8/moe.csv Normal file
View File

@@ -0,0 +1,6 @@
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
0.03094400092959404,0.052000001072883606,0.03423200035467744,0.032816000282764435,0.004586225105504425,0.05225599929690361,0.08137600123882294,0.06316960025578737,0.0586559996008873,0.009046516570964667,0.025087999179959297,0.05766399949789047,0.030939200054854156,0.028768000192940235,0.006844666670168347,0.23388800024986267,0.31091201305389404,0.24544477462768555,0.23836800456047058,0.018666831776499748,16,128,128,1,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
0.030368000268936157,0.05008000135421753,0.03488799966871738,0.03270399942994118,0.004964435488742052,0.05142400041222572,0.07401599735021591,0.05652640014886856,0.054847998544573784,0.005118024227402908,0.02534399926662445,0.0424639992415905,0.02885119989514351,0.028447999618947506,0.004027125677475938,0.24774399399757385,0.26895999908447266,0.25432640314102173,0.25200000405311584,0.00582256680354476,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.6171875,0.0,0.9682458365518543,4.0,6.171569533299451,0.521240234375,uniform,1,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.0307839997112751,0.04447999969124794,0.03474240032956004,0.03252799995243549,0.00435773849976965,0.051231998950242996,0.07468800246715546,0.057651200145483014,0.0561280008405447,0.006050027441177822,0.02579200081527233,0.033504001796245575,0.02867360021919012,0.02796800062060356,0.00238178652420847,0.2533760070800781,0.2958720028400421,0.2585648000240326,0.25679999589920044,0.009045161306858063,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.640625,0.0,0.9842509842514764,4.0,6.193092091810443,0.5164794921875,uniform,2,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030592000111937523,0.04108799993991852,0.03223840007558465,0.031279999762773514,0.002451635813407811,0.05177599936723709,0.077504001557827,0.05718399975448847,0.0533440001308918,0.00711033940595454,0.02457600086927414,0.051552001386880875,0.03192960014566779,0.028431999497115612,0.007824328074264588,0.2531839907169342,0.28329598903656006,0.26060959696769714,0.2584640085697174,0.006803486030548811,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.671875,0.0,0.9354143466934853,5.0,6.268369216857352,0.48486328125,uniform,3,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030527999624609947,0.03500799834728241,0.03184479987248778,0.03139200061559677,0.001123070738289876,0.05104000121355057,0.07103999704122543,0.05895199999213219,0.05676800012588501,0.0068221931474717916,0.024383999407291412,0.04211200028657913,0.02812959998846054,0.026959999464452267,0.003887262202895282,0.2314240038394928,0.2559039890766144,0.23696160316467285,0.23375999927520752,0.006377317477017641,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.59375,0.0,1.1319231422671772,6.0,6.039891775809659,0.5689697265625,uniform,4,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 0.03094400092959404 0.052000001072883606 0.03423200035467744 0.032816000282764435 0.004586225105504425 0.05225599929690361 0.08137600123882294 0.06316960025578737 0.0586559996008873 0.009046516570964667 0.025087999179959297 0.05766399949789047 0.030939200054854156 0.028768000192940235 0.006844666670168347 0.23388800024986267 0.31091201305389404 0.24544477462768555 0.23836800456047058 0.018666831776499748 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
3 0.030368000268936157 0.05008000135421753 0.03488799966871738 0.03270399942994118 0.004964435488742052 0.05142400041222572 0.07401599735021591 0.05652640014886856 0.054847998544573784 0.005118024227402908 0.02534399926662445 0.0424639992415905 0.02885119989514351 0.028447999618947506 0.004027125677475938 0.24774399399757385 0.26895999908447266 0.25432640314102173 0.25200000405311584 0.00582256680354476 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 0.6171875 0.0 0.9682458365518543 4.0 6.171569533299451 0.521240234375 uniform 1 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
4 0.0307839997112751 0.04447999969124794 0.03474240032956004 0.03252799995243549 0.00435773849976965 0.051231998950242996 0.07468800246715546 0.057651200145483014 0.0561280008405447 0.006050027441177822 0.02579200081527233 0.033504001796245575 0.02867360021919012 0.02796800062060356 0.00238178652420847 0.2533760070800781 0.2958720028400421 0.2585648000240326 0.25679999589920044 0.009045161306858063 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 0.640625 0.0 0.9842509842514764 4.0 6.193092091810443 0.5164794921875 uniform 2 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
5 0.030592000111937523 0.04108799993991852 0.03223840007558465 0.031279999762773514 0.002451635813407811 0.05177599936723709 0.077504001557827 0.05718399975448847 0.0533440001308918 0.00711033940595454 0.02457600086927414 0.051552001386880875 0.03192960014566779 0.028431999497115612 0.007824328074264588 0.2531839907169342 0.28329598903656006 0.26060959696769714 0.2584640085697174 0.006803486030548811 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 0.671875 0.0 0.9354143466934853 5.0 6.268369216857352 0.48486328125 uniform 3 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
6 0.030527999624609947 0.03500799834728241 0.03184479987248778 0.03139200061559677 0.001123070738289876 0.05104000121355057 0.07103999704122543 0.05895199999213219 0.05676800012588501 0.0068221931474717916 0.024383999407291412 0.04211200028657913 0.02812959998846054 0.026959999464452267 0.003887262202895282 0.2314240038394928 0.2559039890766144 0.23696160316467285 0.23375999927520752 0.006377317477017641 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 0.59375 0.0 1.1319231422671772 6.0 6.039891775809659 0.5689697265625 uniform 4 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128

27
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/aligned/compute/h20/moe_config.yaml Normal file
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: 5
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles-moe-factorial-r5/aligned
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null

6
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/compute_type/compute/h20/Qwen3-235B-A22B-FP8/moe.csv Normal file
View File

@@ -0,0 +1,6 @@
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
0.03232000023126602,0.07411199808120728,0.040055999718606475,0.03792000003159046,0.010027335937042725,0.05955199897289276,0.09151999652385712,0.06805919948965311,0.06542399898171425,0.009156033646696494,0.02735999971628189,0.04198399931192398,0.031628800183534624,0.03081599995493889,0.0038650835976484594,0.29440000653266907,0.37036800384521484,0.3045775890350342,0.3012160062789917,0.01622786745429039,16,128,128,1,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
0.03190400078892708,0.0639680027961731,0.036531200259923936,0.03387199901044369,0.007307958553439168,0.05407999828457832,0.08684799820184708,0.0631104001775384,0.059248000383377075,0.008437822166776614,0.02537599951028824,0.045343998819589615,0.029841599892824887,0.028095999732613564,0.004578510902843549,0.29868799448013306,0.3216319978237152,0.30579519271850586,0.30294400453567505,0.006667278707027435,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.6171875,0.0,0.9682458365518543,4.0,6.171569533299451,0.521240234375,uniform,1,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.031199999153614044,0.06745599955320358,0.03718719966709614,0.03391999937593937,0.008084069620200455,0.05353600159287453,0.06828799843788147,0.059427200257778166,0.05902400054037571,0.0036973349098869714,0.026688000187277794,0.03788800165057182,0.030459199845790864,0.02908799983561039,0.0032231049972104124,0.30588799715042114,0.3216319978237152,0.3109855651855469,0.31036800146102905,0.004134960938245058,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.640625,0.0,0.9842509842514764,4.0,6.193092091810443,0.5164794921875,uniform,2,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.031488001346588135,0.04790399968624115,0.03488959986716509,0.033615998923778534,0.003995903359891917,0.05503999814391136,0.08563199639320374,0.06150399968028068,0.057312000542879105,0.007950341155323642,0.026335999369621277,0.04598399996757507,0.030313600040972232,0.02792000025510788,0.005356499011224523,0.31516799330711365,0.32972800731658936,0.3209056258201599,0.3196159899234772,0.004338567610830069,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.671875,0.0,0.9354143466934853,5.0,6.268369216857352,0.48486328125,uniform,3,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030751999467611313,0.044895999133586884,0.03544640000909567,0.03302400000393391,0.00457756723742277,0.05331199988722801,0.07606399804353714,0.05961279980838299,0.05753600038588047,0.006503363955077464,0.02630399912595749,0.04368000105023384,0.03112160013988614,0.028815999627113342,0.005258638278682459,0.2905920147895813,0.3538239896297455,0.3015664219856262,0.29631999135017395,0.014866933226585388,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.59375,0.0,1.1319231422671772,6.0,6.039891775809659,0.5689697265625,uniform,4,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 0.03232000023126602 0.07411199808120728 0.040055999718606475 0.03792000003159046 0.010027335937042725 0.05955199897289276 0.09151999652385712 0.06805919948965311 0.06542399898171425 0.009156033646696494 0.02735999971628189 0.04198399931192398 0.031628800183534624 0.03081599995493889 0.0038650835976484594 0.29440000653266907 0.37036800384521484 0.3045775890350342 0.3012160062789917 0.01622786745429039 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
3 0.03190400078892708 0.0639680027961731 0.036531200259923936 0.03387199901044369 0.007307958553439168 0.05407999828457832 0.08684799820184708 0.0631104001775384 0.059248000383377075 0.008437822166776614 0.02537599951028824 0.045343998819589615 0.029841599892824887 0.028095999732613564 0.004578510902843549 0.29868799448013306 0.3216319978237152 0.30579519271850586 0.30294400453567505 0.006667278707027435 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 0.6171875 0.0 0.9682458365518543 4.0 6.171569533299451 0.521240234375 uniform 1 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
4 0.031199999153614044 0.06745599955320358 0.03718719966709614 0.03391999937593937 0.008084069620200455 0.05353600159287453 0.06828799843788147 0.059427200257778166 0.05902400054037571 0.0036973349098869714 0.026688000187277794 0.03788800165057182 0.030459199845790864 0.02908799983561039 0.0032231049972104124 0.30588799715042114 0.3216319978237152 0.3109855651855469 0.31036800146102905 0.004134960938245058 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 0.640625 0.0 0.9842509842514764 4.0 6.193092091810443 0.5164794921875 uniform 2 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
5 0.031488001346588135 0.04790399968624115 0.03488959986716509 0.033615998923778534 0.003995903359891917 0.05503999814391136 0.08563199639320374 0.06150399968028068 0.057312000542879105 0.007950341155323642 0.026335999369621277 0.04598399996757507 0.030313600040972232 0.02792000025510788 0.005356499011224523 0.31516799330711365 0.32972800731658936 0.3209056258201599 0.3196159899234772 0.004338567610830069 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 0.671875 0.0 0.9354143466934853 5.0 6.268369216857352 0.48486328125 uniform 3 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
6 0.030751999467611313 0.044895999133586884 0.03544640000909567 0.03302400000393391 0.00457756723742277 0.05331199988722801 0.07606399804353714 0.05961279980838299 0.05753600038588047 0.006503363955077464 0.02630399912595749 0.04368000105023384 0.03112160013988614 0.028815999627113342 0.005258638278682459 0.2905920147895813 0.3538239896297455 0.3015664219856262 0.29631999135017395 0.014866933226585388 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 0.59375 0.0 1.1319231422671772 6.0 6.039891775809659 0.5689697265625 uniform 4 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128

27
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/compute_type/compute/h20/moe_config.yaml Normal file
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: 5
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles-moe-factorial-r5/compute_type
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null

6
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/config_key/compute/h20/Qwen3-235B-A22B-FP8/moe.csv Normal file
View File

@@ -0,0 +1,6 @@
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
0.029888000339269638,0.05558399856090546,0.036182400118559596,0.03598400019109249,0.00590375348379892,0.05135999992489815,0.07407999783754349,0.05939359981566668,0.05599999986588955,0.007274243962538696,0.024831999093294144,0.060575999319553375,0.03204159988090396,0.029280000366270542,0.008986441399241034,0.23401600122451782,0.2914240062236786,0.24253761768341064,0.23852799832820892,0.012656064704060555,16,128,128,1,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
0.0306560005992651,0.04927999898791313,0.0345616003498435,0.032096000388264656,0.005272357401818311,0.0514880008995533,0.08454400300979614,0.05950720049440861,0.055904000997543335,0.008599599958802731,0.024639999493956566,0.04726399853825569,0.029726399946957825,0.028032000176608562,0.005891950556036845,0.24633599817752838,0.276095986366272,0.2544096112251282,0.25091201066970825,0.006771203130483627,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.6171875,0.0,0.9682458365518543,4.0,6.171569533299451,0.521240234375,uniform,1,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030208000913262367,0.062144000083208084,0.03510080017149449,0.03203200176358223,0.007286512102806094,0.050592001527547836,0.07017599791288376,0.05696159955114126,0.054735999554395676,0.006055532934843585,0.0244159996509552,0.04364800080657005,0.02875520009547472,0.02700799982994795,0.00429941663275523,0.252703994512558,0.27452799677848816,0.25873440504074097,0.2567040026187897,0.006180537864565849,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.640625,0.0,0.9842509842514764,4.0,6.193092091810443,0.5164794921875,uniform,2,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.028863999992609024,0.04185599833726883,0.03244960019364953,0.03129600081592798,0.00309197601199972,0.05049600079655647,0.07241600006818771,0.05591519977897406,0.05273599922657013,0.006825017255220366,0.024000000208616257,0.04150399938225746,0.027609600126743315,0.02619200013577938,0.0041488046270812895,0.25491198897361755,0.27008000016212463,0.2593088150024414,0.25811201333999634,0.003932233899831772,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.671875,0.0,0.9354143466934853,5.0,6.268369216857352,0.48486328125,uniform,3,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030400000512599945,0.039135999977588654,0.03235360030084848,0.031888000667095184,0.002007792126883597,0.050944000482559204,0.06815999746322632,0.054641599953174594,0.053279999643564224,0.003969876178544029,0.024064000695943832,0.03145600110292435,0.027134399861097336,0.026559999212622643,0.0021875101737656014,0.23164799809455872,0.2622720003128052,0.2388928234577179,0.23686400055885315,0.007063580676913261,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.59375,0.0,1.1319231422671772,6.0,6.039891775809659,0.5689697265625,uniform,4,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 0.029888000339269638 0.05558399856090546 0.036182400118559596 0.03598400019109249 0.00590375348379892 0.05135999992489815 0.07407999783754349 0.05939359981566668 0.05599999986588955 0.007274243962538696 0.024831999093294144 0.060575999319553375 0.03204159988090396 0.029280000366270542 0.008986441399241034 0.23401600122451782 0.2914240062236786 0.24253761768341064 0.23852799832820892 0.012656064704060555 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
3 0.0306560005992651 0.04927999898791313 0.0345616003498435 0.032096000388264656 0.005272357401818311 0.0514880008995533 0.08454400300979614 0.05950720049440861 0.055904000997543335 0.008599599958802731 0.024639999493956566 0.04726399853825569 0.029726399946957825 0.028032000176608562 0.005891950556036845 0.24633599817752838 0.276095986366272 0.2544096112251282 0.25091201066970825 0.006771203130483627 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 0.6171875 0.0 0.9682458365518543 4.0 6.171569533299451 0.521240234375 uniform 1 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
4 0.030208000913262367 0.062144000083208084 0.03510080017149449 0.03203200176358223 0.007286512102806094 0.050592001527547836 0.07017599791288376 0.05696159955114126 0.054735999554395676 0.006055532934843585 0.0244159996509552 0.04364800080657005 0.02875520009547472 0.02700799982994795 0.00429941663275523 0.252703994512558 0.27452799677848816 0.25873440504074097 0.2567040026187897 0.006180537864565849 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 0.640625 0.0 0.9842509842514764 4.0 6.193092091810443 0.5164794921875 uniform 2 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
5 0.028863999992609024 0.04185599833726883 0.03244960019364953 0.03129600081592798 0.00309197601199972 0.05049600079655647 0.07241600006818771 0.05591519977897406 0.05273599922657013 0.006825017255220366 0.024000000208616257 0.04150399938225746 0.027609600126743315 0.02619200013577938 0.0041488046270812895 0.25491198897361755 0.27008000016212463 0.2593088150024414 0.25811201333999634 0.003932233899831772 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 0.671875 0.0 0.9354143466934853 5.0 6.268369216857352 0.48486328125 uniform 3 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
6 0.030400000512599945 0.039135999977588654 0.03235360030084848 0.031888000667095184 0.002007792126883597 0.050944000482559204 0.06815999746322632 0.054641599953174594 0.053279999643564224 0.003969876178544029 0.024064000695943832 0.03145600110292435 0.027134399861097336 0.026559999212622643 0.0021875101737656014 0.23164799809455872 0.2622720003128052 0.2388928234577179 0.23686400055885315 0.007063580676913261 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 0.59375 0.0 1.1319231422671772 6.0 6.039891775809659 0.5689697265625 uniform 4 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128

27
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/config_key/compute/h20/moe_config.yaml Normal file
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: 5
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles-moe-factorial-r5/config_key
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null

6
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/original/compute/h20/Qwen3-235B-A22B-FP8/moe.csv Normal file
View File

@@ -0,0 +1,6 @@
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
0.03094400092959404,0.05427199974656105,0.03751839986070991,0.03566399961709976,0.0063355673062837495,0.052960000932216644,0.10150399804115295,0.06679840013384819,0.06265599839389324,0.012010412593353396,0.025087999179959297,0.0607680007815361,0.03164320001378655,0.028655999340116978,0.008879480144565048,0.29548799991607666,0.3161599934101105,0.30511200428009033,0.30371201038360596,0.006655826233327389,16,128,128,1,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
0.030368000268936157,0.045184001326560974,0.03435200024396181,0.03299199976027012,0.003866832846889978,0.053247999399900436,0.10054399818181992,0.061161600053310394,0.05702400021255016,0.010951609505981603,0.025248000398278236,0.039872001856565475,0.029195200372487306,0.027520000003278255,0.003716525371772022,0.29631999135017395,0.3163839876651764,0.30516156554222107,0.30246400833129883,0.0062532913871109486,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.6171875,0.0,0.9682458365518543,4.0,6.171569533299451,0.521240234375,uniform,1,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030688000842928886,0.04044799879193306,0.03336800048127771,0.032368000596761703,0.002819613112867307,0.053568001836538315,0.06889600306749344,0.05800320040434599,0.055616000667214394,0.00500911399891226,0.025631999596953392,0.040991999208927155,0.028961599990725517,0.027951999567449093,0.003321893930324548,0.30828800797462463,0.3516480028629303,0.3159376084804535,0.3127039968967438,0.009800842963159084,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.640625,0.0,0.9842509842514764,4.0,6.193092091810443,0.5164794921875,uniform,2,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.031007999554276466,0.044319998472929,0.03418559962883592,0.03271999955177307,0.0038270996330861703,0.0541439987719059,0.07507199794054031,0.06345439981669188,0.06393599882721901,0.006346258200489106,0.025407999753952026,0.03494400158524513,0.028180800192058087,0.027375999838113785,0.0024874374625372497,0.3179520070552826,0.331712007522583,0.3228943943977356,0.32150399684906006,0.004389750771224499,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.671875,0.0,0.9354143466934853,5.0,6.268369216857352,0.48486328125,uniform,3,vllm_fused,CUDA_EVENT,BF16,generic,method=fp8|act=dynamic|serialized=True|block=128x128
0.030912000685930252,0.04745600000023842,0.03517600009217858,0.03243200108408928,0.005035846835878437,0.053279999643564224,0.09200000017881393,0.06018720027059317,0.05721599981188774,0.008845081624923161,0.025151999667286873,0.04851200059056282,0.0323488000780344,0.02820800058543682,0.0077821073314592575,0.2917119860649109,0.3189440071582794,0.301118403673172,0.29817599058151245,0.008174914866685867,16,128,128,1,standard_fused_topk,logit_topk,softmax_renorm,True,prefill_hot,ffn_like_prefix_20x,8,4096,1536,True,4,128,0.375,1.0,1.0,0.59375,0.0,1.1319231422671772,6.0,6.039891775809659,0.5689697265625,uniform,4,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 0.03094400092959404 0.05427199974656105 0.03751839986070991 0.03566399961709976 0.0063355673062837495 0.052960000932216644 0.10150399804115295 0.06679840013384819 0.06265599839389324 0.012010412593353396 0.025087999179959297 0.0607680007815361 0.03164320001378655 0.028655999340116978 0.008879480144565048 0.29548799991607666 0.3161599934101105 0.30511200428009033 0.30371201038360596 0.006655826233327389 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
3 0.030368000268936157 0.045184001326560974 0.03435200024396181 0.03299199976027012 0.003866832846889978 0.053247999399900436 0.10054399818181992 0.061161600053310394 0.05702400021255016 0.010951609505981603 0.025248000398278236 0.039872001856565475 0.029195200372487306 0.027520000003278255 0.003716525371772022 0.29631999135017395 0.3163839876651764 0.30516156554222107 0.30246400833129883 0.0062532913871109486 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 0.6171875 0.0 0.9682458365518543 4.0 6.171569533299451 0.521240234375 uniform 1 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
4 0.030688000842928886 0.04044799879193306 0.03336800048127771 0.032368000596761703 0.002819613112867307 0.053568001836538315 0.06889600306749344 0.05800320040434599 0.055616000667214394 0.00500911399891226 0.025631999596953392 0.040991999208927155 0.028961599990725517 0.027951999567449093 0.003321893930324548 0.30828800797462463 0.3516480028629303 0.3159376084804535 0.3127039968967438 0.009800842963159084 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 0.640625 0.0 0.9842509842514764 4.0 6.193092091810443 0.5164794921875 uniform 2 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
5 0.031007999554276466 0.044319998472929 0.03418559962883592 0.03271999955177307 0.0038270996330861703 0.0541439987719059 0.07507199794054031 0.06345439981669188 0.06393599882721901 0.006346258200489106 0.025407999753952026 0.03494400158524513 0.028180800192058087 0.027375999838113785 0.0024874374625372497 0.3179520070552826 0.331712007522583 0.3228943943977356 0.32150399684906006 0.004389750771224499 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 0.671875 0.0 0.9354143466934853 5.0 6.268369216857352 0.48486328125 uniform 3 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128
6 0.030912000685930252 0.04745600000023842 0.03517600009217858 0.03243200108408928 0.005035846835878437 0.053279999643564224 0.09200000017881393 0.06018720027059317 0.05721599981188774 0.008845081624923161 0.025151999667286873 0.04851200059056282 0.0323488000780344 0.02820800058543682 0.0077821073314592575 0.2917119860649109 0.3189440071582794 0.301118403673172 0.29817599058151245 0.008174914866685867 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 0.59375 0.0 1.1319231422671772 6.0 6.039891775809659 0.5689697265625 uniform 4 vllm_fused CUDA_EVENT BF16 generic method=fp8|act=dynamic|serialized=True|block=128x128

27
runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles-moe-factorial-r5/original/compute/h20/moe_config.yaml Normal file
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: 5
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles-moe-factorial-r5/original
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null