PR #680 fix gguf regression for large models

fix gguf regression for large models #680

wenhuach21 merged 4 commits into main from update_0722

trigger ut

e0396b9a

try to fix block_wise rtn issue

5f606646

wenhuach21 changed the title ~~trigger ut~~ fix block_wise rtn issue 163 days ago

n1ck-guo approved these changes on 2025-07-22

refine

11949823

wenhuach21 changed the title ~~fix block_wise rtn issue~~ fix gguf regression for large models 163 days ago

wenhuach21 requested a review from

copilot-pull-request-reviewer 163 days ago

copilot-pull-request-reviewer commented on 2025-07-22

clear cuda memory

ac00585c

wenhuach21 merged 21bb06b6 into main 163 days ago

wenhuach21 deleted the update_0722 branch 163 days ago

Reviewers

n1ck-guo

Assignees

No one assigned

Labels

None yet

Milestone

No milestone