vllm/worker/model_runner.py · 187e32997cdc20bbed5c21d3cef2609ab8ed9080 · OpenDAS / vllm_cscc · GitLab

"tests/models/quantization/test_mxfp4.py" did not exist on "f98e3075880bde73f5bdc20ab688e224352f6880"

Find file Blame History Permalink

[Bugfix] Change kv scaling factor by param json on nvidia gpu (#11688) · 187e3299
bjmsong authored Jan 03, 2025
```
Signed-off-by: bjmsong <bjmsong@126.com>
Co-authored-by: bjmsong <bjmsong@126.com>
```
187e3299

model_runner.py 87 KB