intel/auto-round

Pull Requests Commits

support to export static afp8 model (#662)

n1ck-guo committed 241 days ago

Verified 92bbaad3

fix ut import issue (#686)

WeiweiZhang1 committed 241 days ago

Verified 9e475278

bump version into v0.6.0 (#687)

XuehaoSun committed 241 days ago

Verified 5a07e4a7

fix gemma vlm gguf regression (#685)

wenhuach21 committed 242 days ago

Verified 3f36254c

fix gguf regression for large models (#680)

wenhuach21 committed 242 days ago

Verified 21bb06b6

update gguf convert file and fix bug of permute bug (#679)

n1ck-guo committed 243 days ago

Verified 4e1b81f9

rm_old_vlm_cuda_ut (#678)

WeiweiZhang1 committed 243 days ago

Verified 1ead9fe9

rm low_cpu when loading the model (#676)

wenhuach21 committed 243 days ago

Verified 2fe91d77

restrict accelerate version to reduce ram usage (#673)

wenhuach21 committed 244 days ago

Verified 308e5e36

fix 3bits asym accuracy and calib dataset issues (#674)

WeiweiZhang1 committed 244 days ago

Verified bc14beaf

add trust remote code to gguf format load tokenizer (#675)

n1ck-guo committed 244 days ago

Verified 9461bf91

support to use lm_eval for vlm (#670)

n1ck-guo committed 244 days ago

Verified 16b8a262

fix cuda hanging issue during packing (#669)

WeiweiZhang1 committed 247 days ago

Verified 7863f69d

fix ut issue (#668)

WeiweiZhang1 committed 247 days ago

Verified 0a8ebdfb

handle zeros in imatrix (#667)

wenhuach21 committed 247 days ago

Verified c1ea0d98

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

n1ck-guo committed 248 days ago

Verified 923683ae

fix gguf block-wise issue (#664)

wenhuach21 committed 248 days ago

Verified 313f436e

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

n1ck-guo committed 248 days ago

Verified 5d68aeb7

support vlm models for gguf format

n1ck-guo committed 249 days ago

Verified a2f3f016

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

n1ck-guo committed 254 days ago

Verified 750a5c10

fix some issues (#655)

wenhuach21 committed 254 days ago

Verified 2f22e29a

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

wenhuach21 committed 255 days ago

Verified 7d724036

speedup mxfp tuning and fix nvfp bug (#647)

wenhuach21 committed 256 days ago

Verified fddcb5d8

Remove cuda UT dependencies version restrictions (#651)

XuehaoSun committed 256 days ago

Verified 35cf154f

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

n1ck-guo committed 256 days ago

Verified 06e0f520

[W4A8]Fix Packing (#648)

yiliu30 committed 257 days ago

Verified a5fa835e

fix norm_bias_tuning (#639)

wenhuach21 committed 257 days ago

Verified 28b01fe3

support llmcompressor format (#646)

xin3he committed 257 days ago

Verified bba62c2b

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

wenhuach21 committed 260 days ago

Verified 3b282dc9

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

n1ck-guo committed 261 days ago

Verified ba5e35c1

Newer Older