tests/kernels/test_flashinfer.py · 53328d7536b3e8ea4863e351b09e4284f5601cae · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention... · 53328d75
LI MOU authored Aug 21, 2024
```
[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)
```
53328d75

test_flashinfer.py 9.7 KB