auto-round
support packing immediately in new quantization api to save ram usage
#466
Merged

support packing immediately in new quantization api to save ram usage #466

wenhuach21 merged 19 commits into main from qsave
wenhuach21
wenhuach21 support qsave and will set it as the main entry
f60ba155
wenhuach21 wenhuach21 marked this pull request as draft 1 year ago
wenhuach21 fix issues
41acf10e
wenhuach21 fix
ec527f57
wenhuach21 wenhuach21 force pushed from 0c25292f to ec527f57 1 year ago
wenhuach21 Merge branch 'main' into qsave
c3dc82ae
wenhuach21 update
ec8cdce1
wenhuach21 wenhuach21 changed the title support qsave and will set it as the main entry support packing immediately in new quantization entry 1 year ago
wenhuach21 wenhuach21 marked this pull request as ready for review 1 year ago
wenhuach21 wenhuach21 changed the title support packing immediately in new quantization entry support packing immediately in new quantization api 1 year ago
wenhuach21 trigger preci
cef98d5b
wenhuach21 tiny change
858f0093
wenhuach21 tiny change
ddd80ebd
wenhuach21 wenhuach21 changed the title support packing immediately in new quantization api support packing immediately in new quantization api to save ram usage 1 year ago
wenhuach21 try to fix ut
682ef256
wenhuach21 revert one change
a9e9f7e4
wenhuach21 Merge branch 'main' into qsave
ff6c5c9e
wenhuach21 wenhuach21 requested a review from n1ck-guo n1ck-guo 1 year ago
wenhuach21 wenhuach21 requested a review from WeiweiZhang1 WeiweiZhang1 1 year ago
wenhuach21 Merge branch 'main' into qsave
5ea40b5d
wenhuach21 fix merge issue
143f2717
wenhuach21 Merge branch 'main' into qsave
c6a128e2
wenhuach21 fix merge issue
d9a3a42d
wenhuach21 fix ut
b7fe2021
wenhuach21 keep the format order
876869f0
WeiweiZhang1
WeiweiZhang1 approved these changes on 2025-03-19
wenhuach21 refine pbar
1531a75a
wenhuach21 Merge branch 'main' into qsave
1bb1d46e
wenhuach21 wenhuach21 merged 8033dd0d into main 1 year ago
wenhuach21 wenhuach21 deleted the qsave branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone