vllm/model_executor/layers/quantization/modelopt.py · 72b1c2ae2c2d2782ef1850ca1b96a21f797f7af6 · OpenDAS / vllm_cscc · GitLab

"vllm/entrypoints/pooling/embed/serving.py" did not exist on "3729ed00ba4c5a9f351b1241b15a2ca3ca12a5e1"

Find file Blame History Permalink

[Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439) · 72b1c2ae
Pavani Majety authored Nov 07, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
72b1c2ae

modelopt.py 67.7 KB