intel/auto-round

Pull Requests Commits

docs: add svdquant details CN counterpart

Copilot committed 5 days ago

Verified 87fc6199

Potential fix for pull request finding

changwangss committed 6 days ago

Verified 5b346f73

modify the blockforwardrunner cache process

changwangss committed 6 days ago

958006e5

Merge branch 'main' into wangchang/svd

changwangss committed 6 days ago

Verified 29dafaa2

fix device target

changwangss committed 6 days ago

80c60c19

fix performance regression bug (#2136)

n1ck-guo committed 6 days ago

Verified f8ad63f4

changwangss committed 7 days ago

f97fc90e

changwangss committed 7 days ago

fc6e179f

changwangss committed 7 days ago

055592fc

fix: validate SVDQuant calibration config

changwangss committed 7 days ago

e6e4160d

docs: add SVDQuant details

changwangss committed 7 days ago

54321e03

fix: support low-memory diffusion SignRound calibration

changwangss committed 7 days ago

0ba9d0bb

feat: add Nunchaku SVDQuant export

changwangss committed 7 days ago

485c4c64

feat: add SVDQuant serialization codecs

changwangss committed 7 days ago

1fce9d5b

feat: add SVDQuant smooth calibration

changwangss committed 7 days ago

4880488c

feat: add SVDQuant algorithm CLI

changwangss committed 7 days ago

00ddc913

feat: integrate SVDQuant with algorithm composer

changwangss committed 7 days ago

da4c8e80

feat: port SVDQuant core primitives

changwangss committed 7 days ago

00e346ba

Enhance unit tests with timeout handling and stability improvements (#2135)

XuehaoSun committed 7 days ago

Verified e4a02ccd

Add python 3.14t compatibility tests (#2110)

XuehaoSun committed 9 days ago

Verified 98f2cdb9

support one more mxfp4 variant (#2132)

wenhuach21 committed 9 days ago

Verified f706da67

Add llmc test back (#2131)

yiliu30 committed 9 days ago

Verified 1f6b2151

fix sparge on torch2.13 (#2130)

yiliu30 committed 10 days ago

Verified d8a30059

Refator UT and improve code coverage (#2057)

lvliang-intel committed 10 days ago

Verified 7a75218a

[fix] XPU crash due to circle call of nonzero() and index_select() (#2117)

xin3he committed 11 days ago

Verified 28003697

Enable torch.compile for selected tests and update related configurations (#2124)

xin3he committed 11 days ago

Verified a2f6b316

support fused MoE quantization and export for GGUF format (#2072)

n1ck-guo committed 11 days ago

Verified 1fca0c74

refactor scheme,layer_config and formats (#2013)

n1ck-guo committed 12 days ago

Verified 77e8ea59

Automatically select calibration datasets for code models (#2107)

changwangss committed 12 days ago

Verified f8de00c3

disable parallel for non low_gpu_mem_usage (#2116)

xin3he committed 13 days ago

Verified 417d87de

Older