auto-round
refine inference backend/code step 1
#486
Merged

refine inference backend/code step 1 #486

wenhuach21 merged 44 commits into main from refine_auto_qunatizer
wenhuach21
wenhuach21 refine autoround format
1d514cfa
wenhuach21 delete example to sync main
ae14c449
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
90811247
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
7502d605
wenhuach21 fix some issues
47130790
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
43d02f2f
wenhuach21 clean code
12c24ba4
wenhuach21 Merge branch 'refine_auto_qunatizer' of https://github.com/intel/auto…
ec1b4618
wenhuach21 fix some issue
74482ea9
wenhuach21 support device map
949bac3e
wenhuach21 cache backend
72d6655c
wenhuach21 fix preci
bb58f6af
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
0eb79879
wenhuach21 support marlin
9796bd08
wenhuach21 fix some issues
32d15c72
wenhuach21 refine backend a little
7a4cd718
wenhuach21 refine backend a little
32efa294
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
7e5616a9
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
0187f915
wenhuach21 rm cuda code
70ff42c9
wenhuach21 fix preci issue
00bd9212
wenhuach21 marlin and triton kernel are basically ready
9fd5920a
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
49b6e61a
wenhuach21 add exllamav2 kernel ut
b0ccc968
wenhuach21 tiny change
2876dce6
wenhuach21 fix some issues
f90e9976
wenhuach21 fix typo
ef952d2d
wenhuach21 dtype is done
4c307b10
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
3d0945c4
wenhuach21 provide a workaournd for marlin offloading issue
ab6aef39
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
58220434
wenhuach21 fix some issues
bb8c0da3
wenhuach21 fix some issues
ecd296e0
wenhuach21 fix triton multiple gpu issue
c7eee0c2
wenhuach21 wenhuach21 changed the title [WIP]refine auto quantizer refine auto quantizer step 1 343 days ago
wenhuach21 wenhuach21 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 343 days ago
wenhuach21 wenhuach21 removed review request from copilot-pull-request-reviewer copilot-pull-request-reviewer 343 days ago
wenhuach21 wenhuach21 requested a review from n1ck-guo n1ck-guo 343 days ago
wenhuach21 wenhuach21 removed review request from n1ck-guo n1ck-guo 343 days ago
wenhuach21 wenhuach21 requested a review from WeiweiZhang1 WeiweiZhang1 343 days ago
wenhuach21 wenhuach21 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 343 days ago
wenhuach21 wenhuach21 requested a review from n1ck-guo n1ck-guo 343 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2025-04-08
wenhuach21 Update auto_round/export/export_to_autogptq/export.py
797a95eb
wenhuach21 Update auto_round/export/export_to_autoround/export.py
43197f8f
wenhuach21 Update auto_round/export/export_to_awq/export.py
65953d03
wenhuach21 remove gptq:marin from support formats
371c821a
wenhuach21 wenhuach21 changed the title refine auto quantizer step 1 refine inference backend/code step 1 343 days ago
wenhuach21 fix ut
b3fa4078
wenhuach21 fix some issue
db69f91a
n1ck-guo
n1ck-guo approved these changes on 2025-04-09
wenhuach21 fix ut and rm g_idx in packing
c6825517
wenhuach21 recover g_idx packing for auto_gptq format
5c1e2f99
wenhuach21 fix ut
afc8289f
wenhuach21 Merge branch 'main' into refine_auto_qunatizer
984b8a40
wenhuach21 wenhuach21 merged ea4d8435 into main 342 days ago
wenhuach21 wenhuach21 deleted the refine_auto_qunatizer branch 342 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone