intel/auto-round

Pull Requests Commits

yiliu30 committed 162 days ago

60c7194f

Merge branch 'export-afp8' into fp8-cache-based-export

yiliu30 committed 162 days ago

cff43a8b

add fp8 kvcache support

yiliu30 committed 162 days ago

eed46a63

fix cuda hanging issue during packing (#669)

WeiweiZhang1 committed 162 days ago

Verified 7863f69d

fix ut issue (#668)

WeiweiZhang1 committed 162 days ago

Verified 0a8ebdfb

handle zeros in imatrix (#667)

wenhuach21 committed 162 days ago

Verified c1ea0d98

Merge branch 'hengguo/export_static_fp8' of https://github.com/intel/auto-round into hengguo/export_static_fp8

n1ck-guo committed 162 days ago

711282a2

n1ck-guo committed 162 days ago

b51895d6

Merge branch 'main' into hengguo/export_static_fp8

n1ck-guo committed 162 days ago

Verified 58d57ddb

better file name for group_size= 0 or -1

n1ck-guo committed 163 days ago

d87b3ce0

n1ck-guo committed 163 days ago

b212e4ad

n1ck-guo committed 163 days ago

ab701845

fix bugs of export deepseek gguf format when iters=0 and q3k accuracy (#665)

n1ck-guo committed 163 days ago

Verified 923683ae

fix gguf block-wise issue (#664)

wenhuach21 committed 163 days ago

Verified 313f436e

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

n1ck-guo committed 163 days ago

Verified 5d68aeb7

support to export static afp8 model

n1ck-guo committed 163 days ago

4dd6e6b6

support vlm models for gguf format

n1ck-guo committed 164 days ago

Verified a2f3f016

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

n1ck-guo committed 168 days ago

Verified 750a5c10

fix some issues (#655)

wenhuach21 committed 169 days ago

Verified 2f22e29a

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

wenhuach21 committed 169 days ago

Verified 7d724036

speedup mxfp tuning and fix nvfp bug (#647)

wenhuach21 committed 171 days ago

Verified fddcb5d8

Remove cuda UT dependencies version restrictions (#651)

XuehaoSun committed 171 days ago

Verified 35cf154f

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

n1ck-guo committed 171 days ago

Verified 06e0f520

[W4A8]Fix Packing (#648)

yiliu30 committed 172 days ago

Verified a5fa835e

fix norm_bias_tuning (#639)

wenhuach21 committed 172 days ago

Verified 28b01fe3

support llmcompressor format (#646)

xin3he committed 172 days ago

Verified bba62c2b

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

wenhuach21 committed 175 days ago

Verified 3b282dc9

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

n1ck-guo committed 176 days ago

Verified ba5e35c1

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

n1ck-guo committed 177 days ago

Verified 20eed5b6

refine gguf rtn algorithm and fix bugs (#630)

wenhuach21 committed 178 days ago

Verified ef6413b2

Older