benchmarks/kernels/benchmark_trtllm_decode_attention.py · 40f26734b92ededc6e604fa3296c61248b8cc902 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[NVIDIA] Support Flashinfer TRT-LLM Prefill Attention Kernel (#22095) · 83156c7b
elvischenv authored Aug 05, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
83156c7b

benchmark_trtllm_decode_attention.py 7.33 KB