vllm/model_executor/models/mixtral.py · 4abed65c5806d0514432d102f959a1c84d341171 · OpenDAS / vllm_cscc · GitLab

"csrc/vscode:/vscode.git/clone" did not exist on "1825007bf542ecd1614eaf649dd868f50498bb05"

Find file Blame History Permalink

[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7766) · fc911880
Dipika Sikka authored Aug 27, 2024
```
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
```
fc911880

mixtral.py 18.5 KB