def run_torch_mla()

in benchmark/bench_flash_mla.py [0:0]

• 23 lines of code
• 3 McCabe index (conditional complexity)

def run_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):
    for i in range(b):
        blocked_k.view(b, max_seqlen_pad, h_kv, d)[i, cache_seqlens[i].item():] = float("nan")
    blocked_v = blocked_k[..., :dv]

    def ref_mla():
        out = torch.empty(b, s_q, h_q, dv, dtype=torch.float32)
        lse = torch.empty(b, h_q, s_q, dtype=torch.float32)
        for i in range(b):
            begin = i * max_seqlen_pad
            end = begin + cache_seqlens[i]
            O, LSE = scaled_dot_product_attention(
                q[i].transpose(0, 1),
                blocked_k.view(-1, h_kv, d)[begin:end].transpose(0, 1),
                blocked_v.view(-1, h_kv, dv)[begin:end].transpose(0, 1),
                h_q, h_kv,
                is_causal=causal,
            )
            out[i] = O.transpose(0, 1)
            lse[i] = LSE
        return out, lse

    out_torch, lse_torch = ref_mla()
    t = triton.testing.do_bench(ref_mla)
    return out_torch, lse_torch, t