intel/auto-round

Pull Requests Commits

wenhuach21 committed 331 days ago

04b7b355

wenhuach21 committed 331 days ago

860fabf8

fix mix bits issue

wenhuach21 committed 331 days ago

11962195

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

wenhuach21 committed 331 days ago

589e91a8

wenhuach21 committed 331 days ago

87b57b02

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

pre-commit-ci[bot] committed 331 days ago

b53cde5f

wenhuach21 committed 331 days ago

e2287424

W4Afp8 export (#378)

wenhuach21 committed 332 days ago

Verified 7f6e5d40

fixl eval bug (#461)

n1ck-guo committed 332 days ago

Verified 5b95a8e6

20x for awq and 4x for gptq packing speedup (#459)

wenhuach21 committed 335 days ago

Verified c803ce9b

Support force loading into autoround Format (#453)

WeiweiZhang1 committed 336 days ago

Verified a79d1a36

awq exporting bugfix (#456)

WeiweiZhang1 committed 336 days ago

Verified 5ccdb0d1

update eval (#450)

n1ck-guo committed 336 days ago

Verified d51bd5e0

update readme (#455)

wenhuach21 committed 337 days ago

Verified 6bc03336

fix critic bug of mxfp4 (#451)

wenhuach21 committed 339 days ago

Verified abe69c54

step-1 support naive double quant in tuning (#442)

wenhuach21 committed 339 days ago

Verified 66adfb16

bump to v0.4.6 (#449)

XuehaoSun committed 345 days ago

Verified 1a9205a4

set torch compile to false by default (#447)

WeiweiZhang1 committed 349 days ago

Verified b6501629

Refine funcs (#446)

WeiweiZhang1 committed 352 days ago

Verified 3a143284

fix bug of evaluate user model (#444)

n1ck-guo committed 352 days ago

Verified 9aa88036

remove tricky setting in mxfp4 (#445)

wenhuach21 committed 353 days ago

Verified 1ae5031e

[HPU]Fix compile bug when quant layer (#441)

yiliu30 committed 356 days ago

Verified 19601d4e

align auto_quantizer with main branch in Transformers (#437)

WeiweiZhang1 committed 357 days ago

Verified 7d27f670

rm gc collect in packing (#438)

wenhuach21 committed 357 days ago

Verified 082f01e7

fix nblocks issues (#432)

wenhuach21 committed 359 days ago

Verified edc2b034

Fix packing hang, torch compile and force to fp16 at exporting (#430)

wenhuach21 committed 360 days ago

Verified 40ab9825

bump to v0.4.5 (#425)

XuehaoSun committed 1 year ago

Verified 096bc196

fix eval trust_remote_code (#424)

n1ck-guo committed 1 year ago

Verified 5c075a9f

fix cuda UT torch_dtype (#423)

WeiweiZhang1 committed 1 year ago

Verified db8088b2

support to export deepseek v3 gguf format (#416)

n1ck-guo committed 1 year ago

Verified 6a49304e

Older