vllm/model_executor/layers/quantization/mxfp4.py · c17610e2baf5e40b3b0638b272bfe7e04e471bfe · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Bugfix] Only use triton_kernels for MXFP4 on SM90 and SM100 (#29339) · c17610e2
Michael Goin authored Nov 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
c17610e2

mxfp4.py 45.2 KB