intel/auto-round

Pull Requests Commits

wenhuach21 committed 305 days ago

01ded53f

fix device bug at calibration (#587)

wenhuach21 committed 305 days ago

Verified 23c71e39

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

WeiweiZhang1 committed 306 days ago

Verified 9f4d31a3

refact cuda ut to facilitate automation (#559)

n1ck-guo committed 306 days ago

Verified e075d43d

fix awq exporting at group_size=-1 (#579)

wenhuach21 committed 306 days ago

Verified 2bb57c23

add torch backend (#555)

WeiweiZhang1 committed 306 days ago

Verified ce8eedd7

switch to transformers API in cpu ut (#580)

wenhuach21 committed 307 days ago

Verified 6ceaa8af

improve the robustness of parsing vlm config (#577)

wenhuach21 committed 307 days ago

Verified 69749b91

modify default asym 4bits auto-round format to awq, fix save folder typo for mllm (#575)

WeiweiZhang1 committed 308 days ago

Verified c1c8148e

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

n1ck-guo committed 308 days ago

Verified fde99cc8

add gguf accuracy data (#574)

wenhuach21 committed 308 days ago

Verified 3e79ebcf

support for llava-based hf model (#568)

n1ck-guo committed 312 days ago

Verified 91487375

update readme (#571)

wenhuach21 committed 312 days ago

Verified 1bad5ee2

update readme (#569)

wenhuach21 committed 313 days ago

Verified 90fef628

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

n1ck-guo committed 313 days ago

Verified b38d19dc

update habana docker to 1.21.0 (#566)

XuehaoSun committed 314 days ago

Verified 9a23061b

fix typo in backend (#564)

wenhuach21 committed 319 days ago

Verified eee6db4b

support xpu in triton backend (#563)

wenhuach21 committed 319 days ago

Verified f683f99a

add UE5M3 simulation (#562)

wenhuach21 committed 320 days ago

Verified fa41c3d1

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

wenhuach21 committed 323 days ago

Verified a45eadb3

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

n1ck-guo committed 327 days ago

Verified 4b85b512

itrex requires torch<2.7 (#548)

XuehaoSun committed 335 days ago

Verified 2e842a2f

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

n1ck-guo committed 336 days ago

Verified 6a6b5901

update readme (#550)

wenhuach21 committed 336 days ago

Verified 59cf22ed

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

wenhuach21 committed 340 days ago

Verified c6155fdb

fix_quantization_config_for_inference (#542)

WeiweiZhang1 committed 340 days ago

Verified 76576406

freeze pytorch & ipex version in CI (#541)

XuehaoSun committed 341 days ago

Verified 784273ed

bump version into v0.5.1 (#540)

XuehaoSun committed 342 days ago

Verified 336ef66a

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

wenhuach21 committed 342 days ago

Verified d6d6dad1

bump version into v0.5.0 (#538)

XuehaoSun committed 343 days ago

Verified 88e6e3b0

Older