intel/auto-round

Pull Requests Commits

wenhuach21 committed 1 year ago

37f9531a

revert the change

wenhuach21 committed 1 year ago

a4b2aa0d

wenhuach21 committed 1 year ago

7dc3365f

wenhuach21 committed 1 year ago

34d4c6f3

wenhuach21 committed 1 year ago

ea57f417

fix gguf block-wise issue

wenhuach21 committed 1 year ago

5e092dcf

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

wenhuach21 committed 1 year ago

90d55e9f

fix bug of block-wise quant imatrix (#663)

n1ck-guo committed 1 year ago

Verified 5d68aeb7

support vlm models for gguf format

n1ck-guo committed 1 year ago

Verified a2f3f016

support rceil for mxfp

wenhuach21 committed 1 year ago

23183a92

fix bug of q4_0 and q5_0 at iters==0 (#658)

n1ck-guo committed 1 year ago

Verified 750a5c10

fix some issues (#655)

wenhuach21 committed 1 year ago

Verified 2f22e29a

support two more calib datasets and fix embedding layer bug (#653)

wenhuach21 committed 1 year ago

Verified 7d724036

speedup mxfp tuning and fix nvfp bug (#647)

wenhuach21 committed 1 year ago

Verified fddcb5d8

Remove cuda UT dependencies version restrictions (#651)

XuehaoSun committed 1 year ago

Verified 35cf154f

Integrate RTN quantization into GGUF packing to enhance robustness (#644)

n1ck-guo committed 1 year ago

Verified 06e0f520

[W4A8]Fix Packing (#648)

yiliu30 committed 1 year ago

Verified a5fa835e

fix norm_bias_tuning (#639)

wenhuach21 committed 1 year ago

Verified 28b01fe3

support llmcompressor format (#646)

xin3he committed 1 year ago

Verified bba62c2b

support packing immediately for gguf to reduce ram usage (#638)

wenhuach21 committed 1 year ago

Verified 3b282dc9

[BUG FIX] fix bug of deepseek gguf:q*k (#637)

n1ck-guo committed 1 year ago

Verified ba5e35c1

fix gguf bug of moe models and lmhead/embedding bits setting regression (#628)

n1ck-guo committed 1 year ago

Verified 20eed5b6

refine gguf rtn algorithm and fix bugs (#630)

wenhuach21 committed 1 year ago

Verified ef6413b2

fix vlm hf config loading issue (#624)

WeiweiZhang1 committed 1 year ago

Verified 51493904

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

wenhuach21 committed 1 year ago

Verified 5181fa02

refine_doc_0624 (#619)

WeiweiZhang1 committed 1 year ago

Verified b6d24385

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

WeiweiZhang1 committed 1 year ago

Verified 898d630d

fix bug of q5_k_s w/ imatrix (#620)

n1ck-guo committed 1 year ago

Verified 3bbddfcc

FP8 WOQ export (#617)

wenhuach21 committed 1 year ago

Verified efff6ca0

fix double quant sym bug (#616)

wenhuach21 committed 1 year ago

Verified 21ecd8b4

Older