intel/auto-round

Pull Requests Commits

fix llama4 export issue

WeiweiZhang1 committed 199 days ago

b058fc09

add qwen3 shell script

WeiweiZhang1 committed 239 days ago

1b5b5e2f

enable qwen3 sglang int8 quantize

WeiweiZhang1 committed 240 days ago

8a464a18

WeiweiZhang1 committed 251 days ago

87e16158

WeiweiZhang1 committed 251 days ago

dd84a4d8

WeiweiZhang1 committed 251 days ago

470927a0

WeiweiZhang1 committed 253 days ago

e2689878

add save config

WeiweiZhang1 committed 253 days ago

9337aa72

enable llama4 int8 quantization baseline

WeiweiZhang1 committed 253 days ago

456b4d61

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

wenhuach21 committed 253 days ago

Verified 471dae81

patch for vlm (#518)

n1ck-guo committed 253 days ago

Verified f3f017a7

add regex support in layer_config setting (#519)

wenhuach21 committed 254 days ago

Verified d286538f

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

wenhuach21 committed 254 days ago

Verified 23cd60dd

move gguf-dq test to cuda (#520)

n1ck-guo committed 254 days ago

Verified 3774f937

support for more vlms (#390)

n1ck-guo committed 254 days ago

Verified 9c7a443d

add group_size divisible check in backend (#512)

wenhuach21 committed 255 days ago

Verified f55cde94

Update requirements-lib.txt (#513)

yiliu30 committed 255 days ago

Verified c480e832

fix critical bug of get_multimodal_block_names (#509)

n1ck-guo committed 257 days ago

Verified ee890b2c

support rtn via iters==0 (#510)

wenhuach21 committed 258 days ago

Verified 58ca5837

fix setup issue on cuda machine (#511)

wenhuach21 committed 258 days ago

Verified 5801ee94

change to new api in readme (#507)

wenhuach21 committed 258 days ago

Verified 1d63c7be

n1ck-guo committed 258 days ago

Verified 9f5d01c5

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

wenhuach21 committed 258 days ago

Verified ef33b495

fix bug of awq/gptq modules_to_not_convert (#501)

n1ck-guo committed 259 days ago

Verified 9a6f325a

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

wenhuach21 committed 259 days ago

Verified 0328e5b1

refine inference step 2 (#498)

wenhuach21 committed 260 days ago

Verified 37341f5e

refine inference backend/code step 1 (#486)

wenhuach21 committed 260 days ago

Verified ea4d8435

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

n1ck-guo committed 260 days ago

Verified 709b6d38

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

pre-commit-ci[bot] committed 261 days ago

Verified 23447b5d

fix bug of mix dataset (#492)

n1ck-guo committed 262 days ago

Verified 943070ef

Older