vllm/model_executor/layers/linear.py · 2cd402e1692417b7645e4ece11bc2ab91072f47c · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[ Bugfix ] Enabling Loading Models With Fused QKV/MLP on Disk with FP8 (#5921) · 2cd402e1
Robert Shaw authored Jun 28, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
```
2cd402e1

linear.py 34.7 KB