Functionrun_flash_infer(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
benchmark/bench_flash_mla.py:82
Functionrun_flash_mla(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
benchmark/bench_flash_mla.py:63
Functionrun_flash_mla_triton(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
benchmark/bench_flash_mla.py:381
Functionrun_torch_mla(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
benchmark/bench_flash_mla.py:36