intel/auto-round

Pull Requests Commits

refine arg setting

WeiweiZhang1 committed 242 days ago

3444901d

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

pre-commit-ci[bot] committed 242 days ago

78dda1e2

WeiweiZhang1 committed 242 days ago

c712b2c3

Merge branch 'main' into set_disable_opt_rtn_default_2_none

WeiweiZhang1 committed 242 days ago

Verified aaf550e2

[API Change]rename fp_layers to ignore_layers (#1233)

wenhuach21 committed 242 days ago

Verified 0ad224c9

Add FP8 dtype info to quant config (#1228)

yiliu30 committed 243 days ago

Verified afea815e

WeiweiZhang1 committed 243 days ago

2b8bc0a9

set disable_opt_rtn to optional bool and change default value from False to None

WeiweiZhang1 committed 243 days ago

0f283f72

gguf add support for Mistral-Magistral-Devstral and Granite (#1226)

n1ck-guo committed 244 days ago

Verified 6f2f9b9e

[STEP 2] refactor format and export (#1192)

n1ck-guo committed 244 days ago

Verified c2449059

align input scale for moe experts for fp8 (#1216)

SwekeR-463 committed 244 days ago

Verified 41a83773

Add CodeQL analysis workflow configuration (#1223)

XuehaoSun committed 244 days ago

Verified 8c72f5fb

open source alg_ext (#1219)

wenhuach21 committed 244 days ago

Verified 86ae59e3

[pre-commit.ci] pre-commit autoupdate (#1222)

pre-commit-ci[bot] committed 244 days ago

Verified beb1e0cd

fix torch dtype (#1217)

wenhuach21 committed 245 days ago

Verified 46aec783

Extend ark CI test trigger scope (#1218)

chensuyue committed 245 days ago

Verified ded1ea70

Update version (#1215)

XuehaoSun committed 245 days ago

Verified 264679c2

fix calibration device issue in some scenarios (#1213)

wenhuach21 committed 246 days ago

Verified 8c0f01e9

update diffusion args (#1210)

mengniwang95 committed 246 days ago

Verified cf746d46

fix scale dtype (#1207)

wenhuach21 committed 250 days ago

Verified f670a25a

Fix llama4 kv quant (#1205)

mengniwang95 committed 250 days ago

Verified cdd96a88

fix backend issue (#1209)

wenhuach21 committed 250 days ago

Verified 95ffb8d3

remove ark support for cpu (#1206)

wenhuach21 committed 251 days ago

Verified 083b6351

fix bug of new version gptqmodel and fix few cuda ut (#1204)

n1ck-guo committed 251 days ago

Verified 68897933

Revert "set disable_opt_rtn as default for int8 RTN" (#1203)

wenhuach21 committed 252 days ago

Verified b3ec4455

set disable_opt_rtn as default for int8 RTN (#1201)

WeiweiZhang1 committed 252 days ago

Verified 56ad9d82

Add FP8 KV Support for DS (#1180)

yiliu30 committed 255 days ago

Verified d390de00

add online quant & offline sgl api generation cuda UT (#1198)

WeiweiZhang1 committed 255 days ago

Verified 3424d912

fix llama4 kv quant (#1199)

mengniwang95 committed 255 days ago

Verified dd8ce2e3

[Important Change] change mxfp4 to OCP definition (#1200)

wenhuach21 committed 255 days ago

Verified af202029

Older