intel/auto-round

Pull Requests Commits

wenhuach21 committed 201 days ago

b687772f

wenhuach21 committed 201 days ago

7e662398

wenhuach21 committed 201 days ago

0d0db962

q3ks of qwen30B-A3B is fine with these changes, fallbacking the first 10 layers is important

wenhuach21 committed 201 days ago

ae7ee9b2

wenhuach21 committed 203 days ago

5410f906

Merge branch 'main' of https://github.com/intel/auto-round

wenhuach21 committed 204 days ago

7698ebe4

fix not using imatrix for gguf at rtn mode (#623)

wenhuach21 committed 204 days ago

Verified 5181fa02

change to float32 as it's quite important

wenhuach21 committed 204 days ago

0165a542

refine_doc_0624 (#619)

WeiweiZhang1 committed 206 days ago

Verified b6d24385

add auto-round related vllm and transformers UT (#613)

WeiweiZhang1 committed 207 days ago

Verified 898d630d

fix bug of q5_k_s w/ imatrix (#620)

n1ck-guo committed 207 days ago

Verified 3bbddfcc

FP8 WOQ export (#617)

wenhuach21 committed 208 days ago

Verified efff6ca0

fix double quant sym bug (#616)

wenhuach21 committed 212 days ago

Verified 21ecd8b4

support customized mixed bits for gguf (#615)

wenhuach21 committed 212 days ago

Verified e06bdbc3

fix gguf packing bug and moe regression (#614)

wenhuach21 committed 213 days ago

Verified 7d18ddbd

mv some checkers (#611)

wenhuach21 committed 214 days ago

Verified c484bc81

fix gguf bug (#610)

wenhuach21 committed 214 days ago

Verified 40d99f2f

fix lots of gguf critic bugs and support imatrix in rtn mode (#595)

wenhuach21 committed 214 days ago

Verified f9921cdf

fix vlm uttest path error (#601)

WeiweiZhang1 committed 222 days ago

Verified 9ff62aff

support for q4_k_m (#596)

n1ck-guo committed 222 days ago

Verified f3fca303

fix q2k bug (#599)

n1ck-guo committed 222 days ago

Verified f41bb3d5

update readme (#597)

wenhuach21 committed 225 days ago

Verified 45b312dd

rm unnecessary forward to improve speed (#593)

wenhuach21 committed 226 days ago

Verified 23d40a0d

Bump protobuf from 3.20.1 to 3.20.2 in /test/test_cuda (#585)

dependabot[bot] committed 227 days ago

Verified dc6d3895

fix cuda ut (#592)

wenhuach21 committed 227 days ago

Verified 4c3dc073

correct errors of deepseek-r1-0528 recipes (#591)

n1ck-guo committed 228 days ago

Verified 6783fc50

add recipes for deepseek-r1-0528 (#588)

n1ck-guo committed 230 days ago

Verified 9263cc86

Update gguf_accuracy (q3_ks) (#590)

SinpackKonmakan committed 232 days ago

Verified da9efc21

fix device bug at calibration (#587)

wenhuach21 committed 232 days ago

Verified 23c71e39

fix tensor shape mismatch error for API usage (#582)

WeiweiZhang1 committed 233 days ago

Verified 9f4d31a3

Older