Code

Enable gptqmodel#35012

Code

Merged

SunMarc merged 63 commits intohuggingface:mainhuggingface/transformers:mainfrom jiqing-feng:gptqjiqing-feng/transformers:gptqCopy head branch name to clipboardJan 15, 2025

+266-86

Commits

Commits on Nov 29, 2024

• gptqmodel

  Show description for 4c567b3
  jiqing-feng

  committed
  4c567b3

  Copy full SHA for 4c567b3

• fix format

  Show description for 1d8f83e
  jiqing-feng

  committed
  1d8f83e

  Copy full SHA for 1d8f83e

Commits on Dec 2, 2024

• update readme

  Show description for 9f44604
  jiqing-feng

  committed
  9f44604

  Copy full SHA for 9f44604

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  62cd0dd

  Copy full SHA for 62cd0dd

Commits on Dec 3, 2024

• gptqmodel need use checkpoint_format (#1)

  Show description for 8c88315
  

  3 peopleauthored
  8c88315

  Copy full SHA for 8c88315

Commits on Dec 4, 2024

• Revert quantizer_gptq.py (#2)

  Show description for ef0fb56
  LRL-ModelCloud

  authored
  ef0fb56

  Copy full SHA for ef0fb56

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  0191322

  Copy full SHA for 0191322

• limit gptqmodel and optimum version

  Show description for 0655960
  jiqing-feng

  committed
  0655960

  Copy full SHA for 0655960

• fix format

  Show description for be914ea
  jiqing-feng

  committed
  be914ea

  Copy full SHA for be914ea

• fix warning

  Show description for aa9a5c6
  jiqing-feng

  committed
  aa9a5c6

  Copy full SHA for aa9a5c6

• fix version check

  Show description for a4bc251
  jiqing-feng

  committed
  a4bc251

  Copy full SHA for a4bc251

• revert unrelated changes

  Show description for 9ae979b
  jiqing-feng

  committed
  9ae979b

  Copy full SHA for 9ae979b

• enable gptqmodel tests

  Show description for a73a8c2
  jiqing-feng

  committed
  a73a8c2

  Copy full SHA for a73a8c2

• fix requires gptq

  Show description for c18a5f1
  jiqing-feng

  committed
  c18a5f1

  Copy full SHA for c18a5f1

Commits on Dec 5, 2024

• Fix Transformer compat (#3)

  Show description for 27ac615
  

  3 peopleauthored
  27ac615

  Copy full SHA for 27ac615

Commits on Dec 7, 2024

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  d3ad24b

  Copy full SHA for d3ad24b

Commits on Dec 10, 2024

• fix format

  Show description for 3972d2e
  jiqing-feng

  committed
  3972d2e

  Copy full SHA for 3972d2e

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  2612dd7

  Copy full SHA for 2612dd7

• fix format again

  Show description for 99b2ed7
  jiqing-feng

  committed
  99b2ed7

  Copy full SHA for 99b2ed7

Commits on Dec 16, 2024

• update gptqmodel version (#6)

  Show description for ac14b9f
  ZX-ModelCloud

  authored
  ac14b9f

  Copy full SHA for ac14b9f

Commits on Dec 19, 2024

• fix unit test (#5)

  Show description for 0276854
  ZX-ModelCloud

  authored
  0276854

  Copy full SHA for 0276854

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  8bde513

  Copy full SHA for 8bde513

Commits on Dec 20, 2024

• backend is loading_attibutes (#7)

  LRL-ModelCloud

  authored
  4ffc7d1

  Copy full SHA for 4ffc7d1

• fix format and tests

  Show description for 5474f89
  jiqing-feng

  committed
  5474f89

  Copy full SHA for 5474f89

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  f9e7e45

  Copy full SHA for f9e7e45

• fix memory check

  Show description for 99b5f14
  jiqing-feng

  committed
  99b5f14

  Copy full SHA for 99b5f14

Commits on Dec 23, 2024

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  331b56a

  Copy full SHA for 331b56a

• fix device mismatch

  Show description for 409f6a2
  jiqing-feng

  committed
  409f6a2

  Copy full SHA for 409f6a2

• fix result check

  Show description for c996a41
  jiqing-feng

  committed
  c996a41

  Copy full SHA for c996a41

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  84e972c

  Copy full SHA for 84e972c

Commits on Dec 24, 2024

• Update src/transformers/quantizers/quantizer_gptq.py

  Show description for dbf68e8
  

  jiqing-feng

  and

  SunMarc

  authored
  dbf68e8

  Copy full SHA for dbf68e8

• Update src/transformers/quantizers/quantizer_gptq.py

  Show description for f4c2ad3
  

  jiqing-feng

  and

  SunMarc

  authored
  f4c2ad3

  Copy full SHA for f4c2ad3

• Update src/transformers/quantizers/quantizer_gptq.py

  Show description for 9185f8b
  

  jiqing-feng

  and

  SunMarc

  authored
  9185f8b

  Copy full SHA for 9185f8b

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  8d69ba4

  Copy full SHA for 8d69ba4

• Merge branch 'main' into gptq

  MekkCyber

  authored
  226953a

  Copy full SHA for 226953a

• update tests

  Show description for 65ee44b
  jiqing-feng

  committed
  65ee44b

  Copy full SHA for 65ee44b

• review: update docs (#10)

  Qubitium

  authored
  34d0ec0

  Copy full SHA for 34d0ec0

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  9d71301

  Copy full SHA for 9d71301

• review: update docs (#12)

  Show description for 153121a
  Qubitium

  authored
  153121a

  Copy full SHA for 153121a

• update tests for gptqmodel

  Show description for b270b2d
  jiqing-feng

  committed
  b270b2d

  Copy full SHA for b270b2d

• update document (#9)

  Show description for 7120899
  

  ZX-ModelCloud

  and

  Qubitium

  authored
  7120899

  Copy full SHA for 7120899

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  a7fcfd7

  Copy full SHA for a7fcfd7

• typo

  Qubitium

  authored
  8e36a0e

  Copy full SHA for 8e36a0e

• doc note for asymmetric quant

  Qubitium

  authored
  0aef2df

  Copy full SHA for 0aef2df

• typo with apple silicon(e)

  Qubitium

  authored
  31a6baa

  Copy full SHA for 31a6baa

• typo for marlin

  Qubitium

  authored
  d7c8890

  Copy full SHA for d7c8890

Commits on Dec 25, 2024

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  db33fd5

  Copy full SHA for db33fd5

Commits on Dec 26, 2024

• column name revert: review

  Qubitium

  authored
  945f663

  Copy full SHA for 945f663

Commits on Dec 27, 2024

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  fc7b971

  Copy full SHA for fc7b971

Commits on Dec 30, 2024

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  6cb77d5

  Copy full SHA for 6cb77d5

Commits on Jan 3, 2025

• Merge branch 'main' into gptq

  Qubitium

  authored
  2234122

  Copy full SHA for 2234122

Commits on Jan 9, 2025

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  d07ed96

  Copy full SHA for d07ed96

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  a20dfd3

  Copy full SHA for a20dfd3

• doc rocm support

  Qubitium

  authored
  91d12cc

  Copy full SHA for 91d12cc

Commits on Jan 10, 2025

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

  Show description for 1ec6fe7
  

  Qubitium

  and

  stevhliu

  authored
  1ec6fe7

  Copy full SHA for 1ec6fe7

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

  Show description for 7d2b708
  

  Qubitium

  and

  stevhliu

  authored
  7d2b708

  Copy full SHA for 7d2b708

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

  Show description for 8c2a8b3
  

  Qubitium

  and

  stevhliu

  authored
  8c2a8b3

  Copy full SHA for 8c2a8b3

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

  Show description for 053e0ad
  

  Qubitium

  and

  stevhliu

  authored
  053e0ad

  Copy full SHA for 053e0ad

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

  Show description for d3bfbb0
  

  Qubitium

  and

  stevhliu

  authored
  d3bfbb0

  Copy full SHA for d3bfbb0

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

  Show description for 1d883ec
  

  Qubitium

  and

  stevhliu

  authored
  1d883ec

  Copy full SHA for 1d883ec

• Merge branch 'main' into gptq

  Qubitium

  authored
  2806f71

  Copy full SHA for 2806f71

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  25169bd

  Copy full SHA for 25169bd

Commits on Jan 14, 2025

• Merge branch 'main' into gptq

  jiqing-feng

  authored
  5ea104a

  Copy full SHA for 5ea104a