auto-round
Support loading for static quant weight fp8 act fp8
#730
Merged

Support loading for static quant weight fp8 act fp8 #730

yiliu30 merged 69 commits into main from wfp8-afp8
yiliu30
yiliu30 load w8a8
bb947822
yiliu30 refactor
9bef8263
yiliu30 add ut
b30a126f
yiliu30 remove example
eaad3a6e
yiliu30 fix typo
c411ca5f
yiliu30 yiliu30 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 143 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2025-08-12
yiliu30 Merge branch 'main' into wfp8-afp8
98023136
wenhuach21
yiliu30 Update auto_round/export/export_to_autoround/export_to_fp8_woq.py
6597d5ca
yiliu30 Update export_to_fp8_woq.py
9b0f32ff
yiliu30
yiliu30 Merge branch 'main' into wfp8-afp8
c32daa6f
yiliu30 yiliu30 marked this pull request as ready for review 143 days ago
wenhuach21
yiliu30 megre main
c136339c
yiliu30 update shape
5ebca24b
wenhuach21
wenhuach21 commented on 2025-08-25
yiliu30 refactor
03cb2171
yiliu30 Merge branch 'main' into wfp8-afp8
e7280f69
yiliu30 tmp add bk
66388e53
yiliu30 refactor code
17ddd2d0
yiliu30 refine code
808449d7
yiliu30 yiliu30 changed the title Support loading for static quant weight fp8 act fp8 [WIP]Support loading for static quant weight fp8 act fp8 128 days ago
yiliu30 fix device list
f74ed6f6
yiliu30 fix
632cf8a9
yiliu30 refactor code
5b8b29d4
yiliu30 fix
57b4c199
yiliu30 update
bdf5f3e5
yiliu30 fix ut
ce3384f3
yiliu30 Merge branch 'main' into wfp8-afp8
7cea90ed
yiliu30 correct
22d11de1
yiliu30 clean
90826139
yiliu30 Merge branch 'wfp8-afp8' of https://github.com/intel/auto-round into …
6503355b
yiliu30 Merge branch 'main' into wfp8-afp8
b6876334
yiliu30 yiliu30 requested a review from wenhuach21 wenhuach21 127 days ago
yiliu30 yiliu30 changed the title [WIP]Support loading for static quant weight fp8 act fp8 Support loading for static quant weight fp8 act fp8 127 days ago
yiliu30 yiliu30 requested a review from n1ck-guo n1ck-guo 127 days ago
yiliu30 yiliu30 requested a review from WeiweiZhang1 WeiweiZhang1 127 days ago
wenhuach21
wenhuach21 commented on 2025-08-28
wenhuach21
wenhuach21 commented on 2025-08-28
wenhuach21
wenhuach21 commented on 2025-08-28
wenhuach21
wenhuach21 commented on 2025-08-28
wenhuach21
wenhuach21 commented on 2025-08-28
wenhuach21
wenhuach21 commented on 2025-08-28
yiliu30 fix shape
2202856f
yiliu30 Merge branch 'wfp8-afp8' of https://github.com/intel/auto-round into …
10f5753b
yiliu30 merge with main
cc42e47f
yiliu30 fix check
d0b99a8f
yiliu30 clean code
31845d0d
yiliu30
yiliu30 yiliu30 changed the title Support loading for static quant weight fp8 act fp8 [WIP]Support loading for static quant weight fp8 act fp8 122 days ago
yiliu30 yiliu30 marked this pull request as draft 122 days ago
yiliu30 merge
fdecddec
yiliu30 fix backend check
1f2e6749
yiliu30 Merge branch 'main' into wfp8-afp8
b56ad253
yiliu30 update config
4cec318f
yiliu30 revert change
6b2962fd
yiliu30 fix
638718e7
yiliu30 yiliu30 marked this pull request as ready for review 120 days ago
yiliu30 yiliu30 changed the title [WIP]Support loading for static quant weight fp8 act fp8 Support loading for static quant weight fp8 act fp8 120 days ago
yiliu30 fix
4df3e8f7
yiliu30
yiliu30 update
e01603ce
yiliu30 propagate the config
0cdf28b1
yiliu30 pass config to checker
27910da0
yiliu30 add more check
d46acdb2
yiliu30 refine code
fd057993
yiliu30 fix equal check
3d75c276
yiliu30 fix equal check
e0c0d58e
yiliu30 Merge branch 'wfp8-afp8' of https://github.com/intel/auto-round into …
75f2928c
yiliu30 fix get
fa3ec2dd
yiliu30
yiliu30 commented on 2025-09-05
yiliu30
yiliu30 commented on 2025-09-05
yiliu30 yiliu30 requested a review from wenhuach21 wenhuach21 120 days ago
wenhuach21
wenhuach21 commented on 2025-09-05
wenhuach21
wenhuach21 commented on 2025-09-05
wenhuach21
wenhuach21 commented on 2025-09-05
wenhuach21
wenhuach21 commented on 2025-09-05
yiliu30 rename
ad5269e0
yiliu30 update check
35e45ed0
yiliu30 add warning
f4e254ba
yiliu30 Merge branch 'main' into wfp8-afp8
7cba242e
yiliu30 rename check
ff5a1e99
yiliu30 Merge branch 'main' into wfp8-afp8
b98f3db9
yiliu30 rename
50968fd0
yiliu30 Merge branch 'main' into wfp8-afp8
586d6a2e
yiliu30 Merge branch 'main' into wfp8-afp8
5e84ff98
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
abd83acf
yiliu30 Merge branch 'main' into wfp8-afp8
9e2c63f3
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
d332a957
yiliu30 Merge branch 'main' into wfp8-afp8
94508e39
pre-commit-ci[bot] [pre-commit.ci] auto fixes from pre-commit.com hooks
8a4a5334
yiliu30 fix
f05e38ba
wenhuach21
wenhuach21 commented on 2025-09-09
wenhuach21
wenhuach21 commented on 2025-09-09
yiliu30 Merge branch 'main' into wfp8-afp8
d759ca3f
yiliu30 update
c58a61c6
yiliu30 yiliu30 requested a review from wenhuach21 wenhuach21 115 days ago
yiliu30 Merge branch 'main' into wfp8-afp8
c89ffc05
yiliu30 Merge branch 'main' into wfp8-afp8
04ae0fdc
wenhuach21
wenhuach21 commented on 2025-09-10
wenhuach21
wenhuach21 commented on 2025-09-10
wenhuach21
wenhuach21 commented on 2025-09-10
wenhuach21
wenhuach21 approved these changes on 2025-09-10
wenhuach21
yiliu30 fix
2c34244c
yiliu30 Merge branch 'wfp8-afp8' of https://github.com/intel/auto-round into …
b3a09107
yiliu30
yiliu30 yiliu30 merged 09e4d312 into main 114 days ago
yiliu30 yiliu30 deleted the wfp8-afp8 branch 114 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone