intel/auto-round

Pull Requests Commits

wenhuach21 committed 55 days ago

54b2d612

Merge branch 'main' into hadamard_change

wenhuach21 committed 56 days ago

Verified 8c1b4f60

Fix missing extra_config export for unsupported ignore_layers like `mlp.gate` (#1660)

lvliang-intel committed 56 days ago

Verified d2a62b89

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

a009d9a8

Merge branch 'hadamard_change' of https://github.com/intel/auto-round into hadamard_change

wenhuach21 committed 57 days ago

cb09ae51

wenhuach21 committed 57 days ago

7a7276e0

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

ccf86610

Merge branch 'hadamard_change' of https://github.com/intel/auto-round into hadamard_change

wenhuach21 committed 57 days ago

8ac1ceee

wenhuach21 committed 57 days ago

3760a3b7

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

89516fe9

wenhuach21 committed 57 days ago

c07b3b1f

wenhuach21 committed 57 days ago

8ca79734

support opt-125m by AI, it seems that the accuracy dropped after rotation

wenhuach21 committed 57 days ago

936c2f52

wenhuach21 committed 57 days ago

d790ce03

wenhuach21 committed 57 days ago

a978b4c6

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

02ce508f

support not using fast hadamard

wenhuach21 committed 57 days ago

e3c1d93e

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

df143716

Merge branch 'hadamard_change' of https://github.com/intel/auto-round into hadamard_change

wenhuach21 committed 57 days ago

14557026

wenhuach21 committed 57 days ago

f41771c1

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 57 days ago

eb3ee0a4

wenhuach21 committed 57 days ago

c13d24ba

import gptqmodel in confest to avoid error in transformers (#1668)

xin3he committed 57 days ago

Verified 106a3223

add gptqmodel 6.0 compatible change and MTP quantization skip warning. (#1663)

xin3he committed 58 days ago

Verified ac7aa288

wenhuach21 committed 58 days ago

9609db37

o_proj quantization has not been handled

wenhuach21 committed 58 days ago

267b6a26

fix autoscheme accuracy drop bug w/o low_gpu, add CI test (#1658)

WeiweiZhang1 committed 58 days ago

Verified c9a0d77b

Enhance performance test (#1610)

XuehaoSun committed 58 days ago

Verified 5b0d3faa

[pre-commit.ci] pre-commit autoupdate (#1661)

pre-commit-ci[bot] committed 58 days ago

Verified e4f94931

force auto-scheme low_gpu to True in CLI (#1653)

wenhuach21 committed 62 days ago

Verified 0f7dba7d

Newer Older