vllm/model_executor/layers/quantization/mxfp4.py · 5e973209aaf5fa15459555eaa42bcd20ea63aa0d · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[BugFix] Fix type error when assign a trition kernel tensor to a torch.nn.Parameter (#28603) · 5e973209
Zijing Liu authored Nov 13, 2025
```
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
```
5e973209

mxfp4.py 45.7 KB