NVFP4 Loading support #839
add nvfp4 inference qlinear
4ca4c0d8
add ut
715e779f
add nvfp4 backend
404bf7f8
refine code
f5d42275
refine code
430b5b61
refine backend check
af38b3f3
merge main
34224209
update backend alias
4167aa91
tmp commit
fdddc398
yiliu30
marked this pull request as ready for review 130 days ago
tmp wa
48af9b87
rename test file
c0eca55e
rename test file
0dda2f39
refine code
55731903
refine code
622b7b29
Merge branch 'main' into nvfp4
8338a7c7
merge main
e8f93154
add feature check
0645ad6d
yiliu30
changed the title [WIP]NVFP4 Loading support NVFP4 Loading support 129 days ago
fix packing format
e5580cbb
update
a4dd899d
force gs fp32
fea4efd6
update
2b5a7d18
revert
a0327822
update
46a72876
Merge branch 'main' into nvfp4
d2964e94
yiliu30
merged
07513377
into main 129 days ago
yiliu30
deleted the nvfp4 branch 129 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub