auto-round
fix nvfp act quantization bug
#891
Merged

fix nvfp act quantization bug #891

WeiweiZhang1 merged 11 commits into main from fix_nvfp_qact_bug
WeiweiZhang1
WeiweiZhang1 fix nvfp act quantization bug
211c2fbb
wenhuach21
WeiweiZhang1 add cuda ut for moe nvfp quantize
68a38d78
WeiweiZhang1 WeiweiZhang1 requested a review from wenhuach21 wenhuach21 151 days ago
wenhuach21
wenhuach21 commented on 2025-10-14
wenhuach21
wenhuach21 approved these changes on 2025-10-14
wenhuach21
wenhuach21 commented on 2025-10-14
wenhuach21
wenhuach21 commented on 2025-10-14
WeiweiZhang1 add cpu UT, refine cuda UT
9c94b04b
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
19f09d54
WeiweiZhang1 fix ut typo
2f32fec1
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
59e184e9
wenhuach21
wenhuach21 commented on 2025-10-15
WeiweiZhang1 fix cpu ut
2dd7a697
WeiweiZhang1 fixtypo
cb70d6d6
WeiweiZhang1 Merge branch 'main' into fix_nvfp_qact_bug
356f2edf
WeiweiZhang1 enhance experts amax match, refine UT
ffa023d5
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
cf26c2bc
WeiweiZhang1 WeiweiZhang1 merged fbc41c8d into main 149 days ago
WeiweiZhang1 WeiweiZhang1 deleted the fix_nvfp_qact_bug branch 149 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone