Evaluate vLLM 0.20 profiles against Frontier

This commit is contained in:
2026-07-16 23:59:10 +08:00
parent 008324e70c
commit 76107d3e87
33 changed files with 13973 additions and 14 deletions

View File

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