vllm/model_executor/model_loader/utils.py · 6f1db287efaf173acceca7e7d6eef75ba0121fc3 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

VLLM_USE_LIGHTOP and VLLM_USE_OPT_CAT · c1ece8c6
zhuwenwen authored Sep 26, 2025
```
add shared_output and routed_scaling_factor of CompressedTensorsW8A8Int8MoEMethod
```
c1ece8c6

utils.py 16.1 KB