intel/auto-round

Pull Requests Commits

add sym & asym gguf quant for gguf baseline (iter==0) (#573)

n1ck-guo committed 216 days ago

Verified fde99cc8

add gguf accuracy data (#574)

wenhuach21 committed 216 days ago

Verified 3e79ebcf

support for llava-based hf model (#568)

n1ck-guo committed 220 days ago

Verified 91487375

update readme (#571)

wenhuach21 committed 221 days ago

Verified 1bad5ee2

update readme (#569)

wenhuach21 committed 221 days ago

Verified 90fef628

Support for more gguf format and float zp for Q*_1 (#560)

n1ck-guo committed 221 days ago

Verified b38d19dc

update habana docker to 1.21.0 (#566)

XuehaoSun committed 222 days ago

Verified 9a23061b

fix typo in backend (#564)

wenhuach21 committed 227 days ago

Verified eee6db4b

support xpu in triton backend (#563)

wenhuach21 committed 227 days ago

Verified f683f99a

add UE5M3 simulation (#562)

wenhuach21 committed 228 days ago

Verified fa41c3d1

refine xpu requirement/config json and fix several issues (#558)

wenhuach21 committed 231 days ago

Verified a45eadb3

[GGUF STEP4] fix search bug and improve packing & eval speed (#545)

n1ck-guo committed 235 days ago

Verified 4b85b512

itrex requires torch<2.7 (#548)

XuehaoSun committed 243 days ago

Verified 2e842a2f

add recipes for qwen3 8b and 14b (#552)

n1ck-guo committed 244 days ago

Verified 6a6b5901

update readme (#550)

wenhuach21 committed 244 days ago

Verified 59cf22ed

[critic bug]remove redundant round in dq simulation (#543)

wenhuach21 committed 248 days ago

Verified c6155fdb

fix_quantization_config_for_inference (#542)

WeiweiZhang1 committed 248 days ago

Verified 76576406

freeze pytorch & ipex version in CI (#541)

XuehaoSun committed 249 days ago

Verified 784273ed

bump version into v0.5.1 (#540)

XuehaoSun committed 250 days ago

Verified 336ef66a

fix triton multiple gpus and some other issues (#539)

wenhuach21 committed 250 days ago

Verified d6d6dad1

bump version into v0.5.0 (#538)

XuehaoSun committed 251 days ago

Verified 88e6e3b0

fix cuda ut (#537)

n1ck-guo committed 251 days ago

Verified eee1752b

refine readme (#536)

WeiweiZhang1 committed 251 days ago

Verified 3f42eddd

update readme (#531)

wenhuach21 committed 252 days ago

Verified 87579ef0

fix inference issue (#529)

wenhuach21 committed 252 days ago

Verified 322ad6ef

fix bug of cuda ut (#532)

n1ck-guo committed 252 days ago

Verified 03f3dcd6

update mllm readme (#530)

WeiweiZhang1 committed 252 days ago

Verified 5e183681

add backend readme (#528)

wenhuach21 committed 252 days ago

Verified c62cd0fb

fix typos, add model card link for VLMs (#527)

WeiweiZhang1 committed 255 days ago

Verified 45df79c7

fix light config (#526)

WeiweiZhang1 committed 255 days ago

Verified 796f332f

Newer Older