benchmarks/kernels/bench_concat_mla_q.py · 580864d81eb03d9fb1383e1782636ff6a9425fa2 · OpenDAS / vllm_cscc

[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA... · 580864d8

Roberto L. Castro authored Mar 09, 2026


[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>

580864d8

bench_concat_mla_q.py 2.95 KB

Replace bench_concat_mla_q.py