vllm/lora/fully_sharded_layers.py · 67005a07bc0991211ba2acccb3e56c72a47f9def · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Bugfix] Add fully sharded layer for QKVParallelLinearWithLora (#5665) · 67005a07
Jee Li authored Jun 21, 2024
```
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
```
67005a07

fully_sharded_layers.py 12.2 KB