intel/auto-round

Pull Requests Commits

support mllm and untied tiny model

sys-lpot-val committed 48 days ago

b2afde36

replace model with tiny model and fix bug

sys-lpot-val committed 48 days ago

d44fc30b

n1ck-guo committed 51 days ago

b740edc9

n1ck-guo committed 51 days ago

390f997a

n1ck-guo committed 51 days ago

9d26d04e

use get_model_path and remove self.assertTrue/False

xin3he committed 51 days ago

b15adc8d

Merge branch 'main' into ut_refactor

n1ck-guo committed 51 days ago

Verified c6064da0

Add G2-specific `FP8_STATIC` support (#1148)

yiliu30 committed 51 days ago

Verified 547d43f8

n1ck-guo committed 51 days ago

d35b1483

handle key not found issue (#1156)

xin3he committed 51 days ago

Verified dd9579e9

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

pre-commit-ci[bot] committed 51 days ago

03917948

xin3he committed 51 days ago

07b741e2

update norm bias tuning doc (#1155)

wenhuach21 committed 52 days ago

Verified 6723ef0a

fix asym quantization issue (#1158)

wenhuach21 committed 52 days ago

Verified 1c23c741

add more fixtures

xin3he committed 52 days ago

b9a177d0

add get_model_path func

n1ck-guo committed 52 days ago

28ccfae3

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

pre-commit-ci[bot] committed 52 days ago

0f20e5ff

xin3he committed 52 days ago

25694c0e

initial implementation

xin3he committed 52 days ago

ed413217

Revert "[STEP 1] refact output formats" (#1157)

n1ck-guo committed 52 days ago

Verified c91b404e

[STEP 1] refact output formats (#906)

n1ck-guo committed 52 days ago

Verified cf99bb3b

Fix cuda test and llmc test (#1152)

XuehaoSun committed 52 days ago

Verified 07c9f634

add more blog in README (#1147)

xin3he committed 53 days ago

Verified 3f92963c

update cd workflow (#1151)

chensuyue committed 53 days ago

Verified 1ac2f15a

fix bug and support shared_layers in cli (#1138)

xin3he committed 54 days ago

Verified 746f32b6

add new posts and align the format (#1125)

xin3he committed 54 days ago

Verified 32b884e1

Added ark backend (#1075)

Zhenzhong1 committed 55 days ago

Verified 25926469

add llmc for cuda ut (#1145)

yiliu30 committed 55 days ago

Verified 2aeffe78

fix cuda ut fail (#1144)

n1ck-guo committed 55 days ago

Verified d1a41160

add low_cpu_mem_usage in cli (#1146)

n1ck-guo committed 55 days ago

Verified 0b74fe15

Older