aituner/runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles/compute/h20/Qwen3-235B-A22B-FP8/moe.csv

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