intel/auto-round

Pull Requests Commits

[Experimental] Add NVFP4 E5M3 support and related components for model-free quantization (#2123)

xin3he committed 28 minutes ago

Verified 0c0511b5

adjust lrx2 logic to fix its issue in mixed bits scenarios and add more woq support in llmc (#2164)

wenhuach21 committed 2 hours ago

Verified 7e35bd63

fix: support aggregated Granite MoE tensors in gguf export (#2175)

n1ck-guo committed 2 hours ago

Verified 5a24c84a

Enable Torch compilation for throughput tests (#2181)

xin3he committed 7 hours ago

Verified e55beddc

fix DiffusionCompressionOrchestrator missing nsamples (#2179)

changwangss committed 21 hours ago

Verified f239f8c9

Simplify default calibration dataset log (#2162)

changwangss committed 1 day ago

Verified 960dc7f8

Add more test cases to improve CUDA UT coverage (#2159)

lvliang-intel committed 1 day ago

Verified 03a44292

Add support for kimi_k25 INT4 packed source models and related tests (#2156)

xin3he committed 5 days ago

Verified 67437798

Add cpu & xpu nightly test (#2149)

XuehaoSun committed 5 days ago

Verified 436dc247

[ARK] Optimize SYCL-TLA woqgemm_s8 on B70 (#2133)

Zhenzhong1 committed 5 days ago

Verified 2ea60e55

Set the quant_method to auto-round by default (#2138)

Zhenzhong1 committed 5 days ago

Verified abacdadf

Support SVDQuant (#2095)

changwangss committed 5 days ago

Verified ccb36588

refine awq, bugfix (#2115)

WeiweiZhang1 committed 5 days ago

Verified a3af3671

feat: Support world model Cosmos3 (#2040)

lvliang-intel committed 5 days ago

Verified 9181fa95

feat: enable search scale for mxfp in model-free (#2141)

xin3he committed 5 days ago

Verified 9352659f

Add timeout decorators to improve test case stability (#2155)

XuehaoSun committed 5 days ago

Verified cee71092

refine eval, add more option (#2114)

WeiweiZhang1 committed 5 days ago

Verified fe7676de

Migrate cpu sdpa from NS flash attn (#2092)

jijiaz committed 6 days ago

Verified 7402af81

Refactor unit test scripts (#2148)

XuehaoSun committed 6 days ago

Verified 506bd5fa

fix: prevent quantized layers from being reinitialized by Transformers (#2147)

n1ck-guo committed 6 days ago

Verified a5e7393e

feat: add per-head fp8 kv attention calibration (#2044)

zeel2104 committed 9 days ago

Verified f17d9cd4

fix performance regression bug (#2136)

n1ck-guo committed 9 days ago

Verified f8ad63f4

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

XuehaoSun committed 10 days ago

Verified e4a02ccd

Add python 3.14t compatibility tests (#2110)

XuehaoSun committed 12 days ago

Verified 98f2cdb9

support one more mxfp4 variant (#2132)

wenhuach21 committed 12 days ago

Verified f706da67

Add llmc test back (#2131)

yiliu30 committed 12 days ago

Verified 1f6b2151

fix sparge on torch2.13 (#2130)

yiliu30 committed 13 days ago

Verified d8a30059

Refator UT and improve code coverage (#2057)

lvliang-intel committed 13 days ago

Verified 7a75218a

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

xin3he committed 13 days ago

Verified 28003697

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

xin3he committed 13 days ago

Verified a2f6b316

Older