PR #35012 Enable gptqmodel

Enable gptqmodel #35012

SunMarc merged 63 commits into huggingface:main from jiqing-feng:gptq

MekkCyber commented on 2024-11-29

MekkCyber requested a review from

SunMarc 1 year ago

gptqmodel

4c567b36

fix format

1d8f83e3

jiqing-feng marked this pull request as ready for review 1 year ago

jiqing-feng changed the title ~~gptqmodel~~ Enable gptqmodel 1 year ago

jiqing-feng marked this pull request as draft 1 year ago

update readme

9f44604c

Merge branch 'main' into gptq

62cd0dd3

SunMarc commented on 2024-12-02

gptqmodel need use checkpoint_format (#1)

8c883152

Revert quantizer_gptq.py (#2)

ef0fb56c

Merge branch 'main' into gptq

0191322d

limit gptqmodel and optimum version

06559606

fix format

be914eaf

fix warning

aa9a5c61

fix version check

a4bc251e

revert unrelated changes

9ae979b5

enable gptqmodel tests

a73a8c25

fix requires gptq

c18a5f14

Fix Transformer compat (#3)

27ac615f

jiqing-feng marked this pull request as ready for review 1 year ago

Merge branch 'main' into gptq

d3ad24b2

fix format

3972d2e7

Merge branch 'main' into gptq

2612dd7e

fix format again

99b2ed76

SunMarc requested a review from

MekkCyber 1 year ago

update gptqmodel version (#6)

ac14b9f4

fix unit test (#5)

0276854b

Merge branch 'main' into gptq

8bde5135

backend is loading_attibutes (#7)

4ffc7d1c

fix format and tests

5474f898

Merge branch 'main' into gptq

f9e7e453

fix memory check

99b5f145

Merge branch 'main' into gptq

331b56aa

fix device mismatch

409f6a2b

SunMarc commented on 2024-12-23

fix result check

c996a415

Merge branch 'main' into gptq

84e972c9

Update src/transformers/quantizers/quantizer_gptq.py

dbf68e86

Update src/transformers/quantizers/quantizer_gptq.py

f4c2ad3d

Update src/transformers/quantizers/quantizer_gptq.py

9185f8ba

Merge branch 'main' into gptq

8d69ba46

Merge branch 'main' into gptq

226953a6

SunMarc approved these changes on 2024-12-24

SunMarc requested a review from

ArthurZucker 1 year ago

update tests

65ee44bf

review: update docs (#10)

34d0ec06

Merge branch 'main' into gptq

9d713014

review: update docs (#12)

153121ae

update tests for gptqmodel

b270b2d8

update document (#9)

7120899c

Merge branch 'main' into gptq

a7fcfd77

typo

8e36a0e9

Qubitium approved these changes on 2024-12-24

MekkCyber approved these changes on 2024-12-24

doc note for asymmetric quant

0aef2df7

typo with apple silicon(e)

31a6baaa

Qubitium approved these changes on 2024-12-24

typo for marlin

d7c88902

Qubitium approved these changes on 2024-12-24

Merge branch 'main' into gptq

db33fd5c

column name revert: review

945f6633

Merge branch 'main' into gptq

fc7b9719

Merge branch 'main' into gptq

6cb77d5a

Merge branch 'main' into gptq

22341228

Merge branch 'main' into gptq

d07ed96d

jiqing-feng requested a review from

Rocketknight1 1 year ago

jiqing-feng requested a review from

stevhliu 1 year ago

ArthurZucker commented on 2025-01-09

Merge branch 'main' into gptq

a20dfd3c

doc rocm support

91d12ccf

stevhliu approved these changes on 2025-01-09

Update docs/source/en/quantization/gptq.md

1ec6fe76

Update docs/source/en/quantization/gptq.md

7d2b7085

Update docs/source/en/quantization/gptq.md

8c2a8b38

Update docs/source/en/quantization/gptq.md

053e0adc

Update docs/source/en/quantization/overview.md

d3bfbb00

Update docs/source/en/quantization/overview.md

1d883ec0

Merge branch 'main' into gptq

2806f716

SunMarc requested a review from

ArthurZucker 1 year ago

Merge branch 'main' into gptq

25169bd5

Merge branch 'main' into gptq

5ea104aa

SunMarc merged 387663e5 into main 1 year ago

Qubitium deleted the gptq branch 1 year ago

Reviewers

stevhliu

SunMarc

Qubitium

MekkCyber

ArthurZucker

Rocketknight1

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

transformers Enable gptqmodel #35012 Merged

Enable gptqmodel #35012

transformers
Enable gptqmodel
#35012

Merged