vllm/model_executor/models/llama.py · 45ac4ff270b267765457159c0b75e1bb7ebf6d79 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[bugfix] fix aria model and add torch.compile (#10645) · 45ac4ff2
youkaichao authored Nov 25, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
45ac4ff2

llama.py 27.6 KB