intel/auto-round

Pull Requests Commits

fix llama4 export issue

WeiweiZhang1 committed 361 days ago

b058fc09

add qwen3 shell script

WeiweiZhang1 committed 1 year ago

1b5b5e2f

enable qwen3 sglang int8 quantize

WeiweiZhang1 committed 1 year ago

8a464a18

WeiweiZhang1 committed 1 year ago

87e16158

WeiweiZhang1 committed 1 year ago

dd84a4d8

WeiweiZhang1 committed 1 year ago

470927a0

WeiweiZhang1 committed 1 year ago

e2689878

add save config

WeiweiZhang1 committed 1 year ago

9337aa72

enable llama4 int8 quantization baseline

WeiweiZhang1 committed 1 year ago

456b4d61

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

wenhuach21 committed 1 year ago

Verified 471dae81

patch for vlm (#518)

n1ck-guo committed 1 year ago

Verified f3f017a7

add regex support in layer_config setting (#519)

wenhuach21 committed 1 year ago

Verified d286538f

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

wenhuach21 committed 1 year ago

Verified 23cd60dd

move gguf-dq test to cuda (#520)

n1ck-guo committed 1 year ago

Verified 3774f937

support for more vlms (#390)

n1ck-guo committed 1 year ago

Verified 9c7a443d

add group_size divisible check in backend (#512)

wenhuach21 committed 1 year ago

Verified f55cde94

Update requirements-lib.txt (#513)

yiliu30 committed 1 year ago

Verified c480e832

fix critical bug of get_multimodal_block_names (#509)

n1ck-guo committed 1 year ago

Verified ee890b2c

support rtn via iters==0 (#510)

wenhuach21 committed 1 year ago

Verified 58ca5837

fix setup issue on cuda machine (#511)

wenhuach21 committed 1 year ago

Verified 5801ee94

change to new api in readme (#507)

wenhuach21 committed 1 year ago

Verified 1d63c7be

n1ck-guo committed 1 year ago

Verified 9f5d01c5

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

wenhuach21 committed 1 year ago

Verified ef33b495

fix bug of awq/gptq modules_to_not_convert (#501)

n1ck-guo committed 1 year ago

Verified 9a6f325a

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

wenhuach21 committed 1 year ago

Verified 0328e5b1

refine inference step 2 (#498)

wenhuach21 committed 1 year ago

Verified 37341f5e

refine inference backend/code step 1 (#486)

wenhuach21 committed 1 year ago

Verified ea4d8435

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

n1ck-guo committed 1 year ago

Verified 709b6d38

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

pre-commit-ci[bot] committed 1 year ago

Verified 23447b5d

fix bug of mix dataset (#492)

n1ck-guo committed 1 year ago

Verified 943070ef

Older