intel/auto-round

Pull Requests Commits
Fix nvfp4&fp8 packing ram issue, refine all exporting format ram release for origin layer (#1129)
yiliu30 committed 33 days ago
Verified 77712681
fix bug of outside block layers do not use best_params (#1128)
n1ck-guo committed 33 days ago
Verified ba1c76cd
Use modelscope cache in CPU UT (#1124)
XuehaoSun committed 34 days ago
Verified fb43723c
fix bug of triton pow wrong data_type when enable torch compile (#1120)
n1ck-guo committed 35 days ago
Verified 3a5010d0
fix gguf extension bug (#1116)
wenhuach21 committed 35 days ago
Verified bd631496
remove result to cpu (#1115)
yiliu30 committed 36 days ago
Verified 5346cb73
fix quant fp8 model with iters=0 and scheme=nvfp4 (#1114)
n1ck-guo committed 36 days ago
Verified 99e4e75e
fix gguf packing device (#1105)
n1ck-guo committed 36 days ago
Verified 4f64730f
fix release version cuda ut fail (#1110)
n1ck-guo committed 36 days ago
Verified c9ac9a4d
fix auto-scheme/alg-ext multiple devices issue (#1107)
wenhuach21 committed 36 days ago
Verified 3e26b0d9
remove non-essential requirements (#1103)
n1ck-guo committed 36 days ago
Verified 36749155
move packeding res to cpu (#1104)
yiliu30 committed 36 days ago
Verified daa151d4
refine lmhead ut (#1106)
WeiweiZhang1 committed 37 days ago
Verified 814cf123
Update README.md (#1102)
xin3he committed 38 days ago
Verified e8714e8a
Add Python 3.14 support to compatibility test pipeline (#1096)
XuehaoSun committed 40 days ago
Verified 99bf7720
fix gguf acc and oom bug when iters > 0 (#1098)
n1ck-guo committed 40 days ago
Verified 09d9962a
Refactor input normalization by replaying inputs for consistent preprocessing (#1094)
yiliu30 committed 40 days ago
Verified 152f1a04
add system checker in backend (#1097)
wenhuach21 committed 40 days ago
Verified ae4ac94c
bump version to v0.9.3 (#1091)
chensuyue committed 41 days ago
Verified f81af704
remove accelerate version limitation (#1090)
chensuyue committed 41 days ago
Verified 39b0643b
Fix MXFP/NVFP + FP8 Attn/KV (#1086)
yiliu30 committed 42 days ago
Verified caa246f9
remove numpy restriction for gptq kernel (#1084)
wenhuach21 committed 42 days ago
Verified 0abae385
fix mxfp qdq (#1088)
yiliu30 committed 42 days ago
Verified cd9f20e8
Support alg_ext on windows (#1082)
chensuyue committed 42 days ago
Verified ed07303d
adjust 3 bits hyperparameters at auto-round-best (#1081)
wenhuach21 committed 43 days ago
Verified ef78c688
fix bf16 option in AutoScheme (#1079)
wenhuach21 committed 44 days ago
Verified 5329bcda
refine sampler (#1077)
wenhuach21 committed 47 days ago
Verified 727e573e
Support mxfp nvfp lmhead quant (#1051)
WeiweiZhang1 committed 47 days ago
Verified c4a14799
improve accuracy for 2bit with auto-round-best (#1078)
wenhuach21 committed 47 days ago
Verified 7907c329
Add MXFP8 MOE/Linear and MXFP4 Linear (#1034)
yiliu30 committed 47 days ago
Verified 61bcfdb6
Terms Of Use Privacy Policy Refund Policy Impressum