awq/modules/fused/attn.py · 92a403b29ffb23848564d45354912f91d20c7f38 · OpenDAS / AutoAWQ · GitLab

Find file Blame History Permalink

[`core` / `attention`] Fix fused attention generation with newest transformers version (#146) · 92a403b2
Younes Belkada authored Nov 04, 2023
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
92a403b2

attn.py 9.86 KB