vllm/model_executor/layers/quantization/mxfp4.py · e5f599d4d1cfd34a5216cf0733d152ea42073f28 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410) · e5f599d4
Michael Goin authored Nov 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
e5f599d4

mxfp4.py 45.7 KB