transformers
Keep MXFP4 weights quantized on XPU when use_kernels is set
#47923
Merged
Overview
Commits
3
Changes
View On GitHub

Keep MXFP4 weights quantized on XPU when use_kernels is set #47923

SunMarc merged 3 commits into huggingface:main from jiqing-feng:xpu-mxfp4-megablocks
jiqing-feng
jiqing-feng Keep MXFP4 weights quantized on XPU when use_kernels is set
bde944aa
Rocketknight1
SunMarc
SunMarc approved these changes on 2026-08-12
HuggingFaceDocBuilderDev
jiqing-feng
jiqing-feng jiqing-feng marked this pull request as ready for review 2 days ago
jiqing-feng Merge branch 'main' into xpu-mxfp4-megablocks
94863c09
jiqing-feng
SunMarc Merge branch 'main' into xpu-mxfp4-megablocks
1e2bf86a
github-actions
SunMarc SunMarc enabled auto-merge 2 days ago
github-actions
SunMarc SunMarc merged e15ea9b9 into main 2 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum