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

1	time_stats.attn_input_reshape.min	time_stats.attn_input_reshape.max	time_stats.attn_input_reshape.mean	time_stats.attn_input_reshape.median	time_stats.attn_input_reshape.std	time_stats.attn_kv_cache_save.min	time_stats.attn_kv_cache_save.max	time_stats.attn_kv_cache_save.mean	time_stats.attn_kv_cache_save.median	time_stats.attn_kv_cache_save.std	time_stats.attn_prefill.min	time_stats.attn_prefill.max	time_stats.attn_prefill.mean	time_stats.attn_prefill.median	time_stats.attn_prefill.std	time_stats.attn_decode.min	time_stats.attn_decode.max	time_stats.attn_decode.mean	time_stats.attn_decode.median	time_stats.attn_decode.std	time_stats.attn_output_reshape.min	time_stats.attn_output_reshape.max	time_stats.attn_output_reshape.mean	time_stats.attn_output_reshape.median	time_stats.attn_output_reshape.std	n_embd	n_q_head	n_kv_head	block_size	num_tensor_parallel_workers	max_model_len	batch_size	prefill_chunk_size	kv_cache_size	is_prefill	attention_backend	is_mixed_batch	mode	seq_lens	total_tokens	max_seq_len	min_seq_len	avg_seq_len	equal_seq_len	seq_len_variance	seq_len_std	seq_len_cv	is_chunked_prefill_sample	chunk_start_token	chunk_end_token	total_prefill_tokens	profiling_precision	model_arch	quant_signature	measurement_type
2	0.010463999584317207	0.04681599885225296	0.018502399697899817	0.01104000024497509	0.014205381674858167	0.021247999742627144	0.033055998384952545	0.025439999625086786	0.024639999493956566	0.004202660707027564	0.05206400156021118	0.09040000289678574	0.0665344014763832	0.06451199948787689	0.013110543934264527	0.007327999919652939	0.011680000461637974	0.008480000123381615	0.0077760000713169575	0.0016149067494504018	0.009472000412642956	0.011103999800980091	0.010118400119245053	0.009600000455975533	0.0007061491557578713	4096	64	4	16	4	40960	1	128	0	True	FLASHINFER	False	even	[128]	128	128	128	128.0	128	0.0	0.0	0.0	False	0	128	128	BF16	generic	method=fp8|act=dynamic|serialized=True|block=128x128	CUDA_EVENT
3	0.010751999914646149	0.012896000407636166	0.011795200034976005	0.011359999887645245	0.0009191526000700493	0.020191999152302742	0.02755199931561947	0.02319999970495701	0.021247999742627144	0.002944486774412461	0.049215998500585556	0.06700800359249115	0.05813760012388229	0.058240000158548355	0.006895964777123649	0.007519999984651804	0.009727999567985535	0.008140799775719642	0.007807999849319458	0.0008127242879711131	0.009472000412642956	0.025248000398278236	0.01303040012717247	0.010015999898314476	0.0061233119538994085	4096	64	4	16	4	40960	1	32	0	True	FLASHINFER	False	even	[32]	32	32	32	32.0	32	0.0	0.0	0.0	False	0	32	32	BF16	generic	method=fp8|act=dynamic|serialized=True|block=128x128	CUDA_EVENT
4	0.010239999741315842	0.011008000001311302	0.010515199974179268	0.010432000271975994	0.0002635681936991548	0.02112000063061714	0.03843199834227562	0.025894399732351303	0.023231999948620796	0.006378760808481684	0.05417599901556969	0.06438399851322174	0.05709439888596535	0.055615998804569244	0.003697870830170538	0.007135999854654074	0.00774399982765317	0.007500800024718046	0.007552000228315592	0.0002009640969704077	0.009279999881982803	0.012736000120639801	0.01031040009111166	0.009568000212311745	0.0012940667684018582	4096	64	4	16	4	40960	1	64	0	True	FLASHINFER	False	even	[64]	64	64	64	64.0	64	0.0	0.0	0.0	False	0	64	64	BF16	generic	method=fp8|act=dynamic|serialized=True|block=128x128	CUDA_EVENT
5	0.010367999784648418	0.02332800067961216	0.013459200039505959	0.010847999714314938	0.004984552697426283	0.02054399996995926	0.0261439997702837	0.02255360037088394	0.022112000733613968	0.001928344367854761	0.04851200059056282	0.07968000322580338	0.058873600512743	0.056352000683546066	0.010813603870069636	0.00723200011998415	0.008352000266313553	0.007686400134116411	0.007648000027984381	0.00039524862182609345	0.008960000239312649	0.011103999800980091	0.009881599992513656	0.00940799992531538	0.0009090251198168286	4096	64	4	16	4	40960	1	96	0	True	FLASHINFER	False	even	[96]	96	96	96	96.0	96	0.0	0.0	0.0	False	0	96	96	BF16	generic	method=fp8|act=dynamic|serialized=True|block=128x128	CUDA_EVENT