intel/auto-round

Pull Requests Commits

Yi4Liu committed 351 days ago

d752280d

tune bf16 to fp8 scale

Yi4Liu committed 352 days ago

14203d64

Yi4Liu committed 352 days ago

997a43b7

Yi4Liu committed 358 days ago

14a59a2b

Yi4Liu committed 1 year ago

2e27ca33

wenhuach21 committed 1 year ago

f899cbf0

Yi4Liu committed 1 year ago

9f281d72

fixed a critic bug

wenhuach21 committed 1 year ago

4b3ea1b5

copy val instead of assign

Yi4Liu committed 1 year ago

80fb3f8d

export two scales

wenhuach21 committed 1 year ago

e9df1217

use bf16 and disable some imports

Yi4Liu committed 1 year ago

88ec7f41

support gptq exporting

wenhuach21 committed 1 year ago

8dddf80f

fix some issues

wenhuach21 committed 1 year ago

5b29135d

wenhuach21 committed 1 year ago

310cf213

fix typos (#377)

wenhuach21 committed 1 year ago

Verified dba15cf9

fix gpu ut (#376)

n1ck-guo committed 1 year ago

Verified 2ffadfd2

Add gpu ut (#370)

wenhuach21 committed 1 year ago

Verified ecc17be0

save processor automatically (#372)

n1ck-guo committed 1 year ago

Verified e4528e92

fix bias issue in autogptq (#375)

wenhuach21 committed 1 year ago

Verified 3ac377b1

[HPU] Add lazy mode back (#371)

yiliu30 committed 1 year ago

Verified 7acb7844

quant_block_names enhancement (#369)

WeiweiZhang1 committed 1 year ago

Verified 67281e2f

using multicard when device set to "auto" (#368)

n1ck-guo committed 1 year ago

Verified b2944b91

add gpu test (#367)

wenhuach21 committed 1 year ago

Verified 1a250eb3

fix bug of only_text_test check due to inference issue on cpu (#362)

n1ck-guo committed 1 year ago

Verified 3acb1191

fix awq exporting bugs (#365)

wenhuach21 committed 1 year ago

Verified d080ea0a

fix awq backend and fp_layers issue (#363)

wenhuach21 committed 1 year ago

Verified 9b9eeb67

Tensor reshape bugfix (#364)

WeiweiZhang1 committed 1 year ago

Verified 3ec66bd9

fix awq exporting (#358)

wenhuach21 committed 1 year ago

Verified ca9e655e

add QWQ-32B, VLM, Qwen2.5, Llama3.1 int4 models (#356)

wenhuach21 committed 1 year ago

Verified 174b7cc3

Simulated W4Afp8 Quantization (#331)

wenhuach21 committed 1 year ago

Verified a98175ff

Older