intel/auto-round

Pull Requests Commits

update convert_hf_to_gguf to support more models (#524)

n1ck-guo committed 299 days ago

Verified aabf1d55

rm fp16 export in autoround format (#525)

wenhuach21 committed 300 days ago

Verified 5d822666

fix examples model_dtype (#523)

WeiweiZhang1 committed 300 days ago

Verified 530bde99

rename backend to packing_format in config.json (#521)

wenhuach21 committed 301 days ago

Verified 471dae81

patch for vlm (#518)

n1ck-guo committed 301 days ago

Verified f3f017a7

add regex support in layer_config setting (#519)

wenhuach21 committed 301 days ago

Verified d286538f

fix bs!=1 for gemma and MiniMax-Text-01 (#515)

wenhuach21 committed 302 days ago

Verified 23cd60dd

move gguf-dq test to cuda (#520)

n1ck-guo committed 302 days ago

Verified 3774f937

support for more vlms (#390)

n1ck-guo committed 302 days ago

Verified 9c7a443d

add group_size divisible check in backend (#512)

wenhuach21 committed 303 days ago

Verified f55cde94

Update requirements-lib.txt (#513)

yiliu30 committed 303 days ago

Verified c480e832

fix critical bug of get_multimodal_block_names (#509)

n1ck-guo committed 305 days ago

Verified ee890b2c

support rtn via iters==0 (#510)

wenhuach21 committed 306 days ago

Verified 58ca5837

fix setup issue on cuda machine (#511)

wenhuach21 committed 306 days ago

Verified 5801ee94

change to new api in readme (#507)

wenhuach21 committed 306 days ago

Verified 1d63c7be

n1ck-guo committed 306 days ago

Verified 9f5d01c5

use --tasks to control evaluation enabling (#505)

wenhuach21 committed 306 days ago

Verified ef33b495

fix bug of awq/gptq modules_to_not_convert (#501)

n1ck-guo committed 306 days ago

Verified 9a6f325a

change quantization method name and made several refinements (#500)

wenhuach21 committed 307 days ago

Verified 0328e5b1

refine inference step 2 (#498)

wenhuach21 committed 308 days ago

Verified 37341f5e

refine inference backend/code step 1 (#486)

wenhuach21 committed 308 days ago

Verified ea4d8435

[GGUF support step3]patch for double quant (#473)

n1ck-guo committed 308 days ago

Verified 709b6d38

[pre-commit.ci] pre-commit autoupdate (#494)

pre-commit-ci[bot] committed 309 days ago

Verified 23447b5d

fix bug of mix dataset (#492)

n1ck-guo committed 310 days ago

Verified 943070ef

update 2bits acc results (#491)

WeiweiZhang1 committed 310 days ago

Verified 226d2bfc

fix llama 8b time cost (#490)

WeiweiZhang1 committed 314 days ago

Verified eb793488

fix dataset combine bug (#489)

wenhuach21 committed 315 days ago

Verified 0d0e1cb3

bump into v0.4.7 (#487)

XuehaoSun committed 316 days ago

Verified f55b6de9

add light ut, fixtypos (#483)

WeiweiZhang1 committed 316 days ago

Verified 7b5a2f1b

support xpu in tuning and inference (#481)

wenhuach21 committed 316 days ago

Verified 1603573a

Newer Older