benchmarks/kernels/benchmark_trtllm_prefill_attention.py · 38d8096760cd8f42fb65fc0ba2b9fb11f98d8ac3 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Flashinfer] Support Flashinfer TRTLLM FP8-qkv BF16/FP16-out Attention Kernel (#23647) · bba1042c
elvischenv authored Sep 09, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
bba1042c

benchmark_trtllm_prefill_attention.py 9.43 KB