Add AutoRound quantization support #37393
add auto-round support
d6a5018c
wenhuach21
marked this pull request as draft 255 days ago
Update src/transformers/quantizers/auto.py
6b2787f1
fix style issue
def1c614
tiny change
78d51780
tiny change
17f2d88e
merge
e8bc8d29
refine ut and doc
b962426d
revert unnecessary change
fa334c4d
tiny change
a8874d61
try to fix style issue
2f82a658
try to fix style issue
02f677e1
try to fix style issue
d5c59b63
try to fix style issue
0906a1e5
try to fix style issue
509b76ed
try to fix style issue
55ce95f7
try to fix style issue
a5246e0f
wenhuach21
marked this pull request as ready for review 254 days ago
fix doc issue
afbf3d94
Update tests/quantization/autoround/test_auto_round.py
910812cb
fix comments
6079ebda
Merge branch 'main' into main
5033e451
Merge branch 'main' into main
c31a65ad
Merge branch 'main' into main
a85c9779
Update tests/quantization/autoround/test_auto_round.py
cdbb5d10
Update tests/quantization/autoround/test_auto_round.py
5a11d681
update doc
988c2d52
Update src/transformers/quantizers/quantizer_auto_round.py
9e76d4c7
update
d624990c
update
e2cc3647
fix
489327a8
try to fix style issue
8ef52090
Merge branch 'main' into main
7d1833a2
Update src/transformers/quantizers/auto.py
3f092903
Merge branch 'main' into main
e2dabcc8
Update docs/source/en/quantization/auto_round.md
57c8c41d
Update docs/source/en/quantization/auto_round.md
ec030d27
Update docs/source/en/quantization/auto_round.md
b283b74c
update
0de3b1eb
fix style issue
9d916834
update doc
502bbd62
update doc
13489509
Refine the doc
f3bfeccb
refine doc
1207667f
revert one change
74145d29
set sym to True by default
a904cfa8
Enhance the unit test's robustness.
85ac0506
update
0629cd05
add torch dtype
d8d182bc
tiny change
9889a276
Merge branch 'main' into main
d9fffecb
add awq convert test
0a64c745
Merge branch 'main' of https://github.com/wenhuach21/transformers
abc8e19f
fix typo
d92b2735
update
33950203
Merge branch 'main' into main
55992537
Merge branch 'main' into main
92efeae8
SunMarc
approved these changes
on 2025-04-22
Merge branch 'main' into main
785d02fc
fix packing format issue
c7071219
Merge branch 'main' of https://github.com/wenhuach21/transformers
01edfb51
use one gpu
73d94830
MekkCyber
merged
b3492ff9
into main 242 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub