intel/auto-round

Pull Requests Commits

Copilot committed 48 days ago

Verified 8bd2b95e

add auto_round_rtn cli and remove fast (#1808)

n1ck-guo committed 48 days ago

Verified debba756

Feats: Quantize/save/evaluate the Wan-AI/WAN2.2 models in w4a16 format (#1678)

lvliang-intel committed 48 days ago

Verified f1db02a3

[bug fix] model free: fix copy folder of diffusion model, fix unresponsive disable_model_free, and cuda UT (#1809)

xin3he committed 48 days ago

Verified 2c915bbd

[step 1]adjust gguf tuning algorithm (#1649)

wenhuach21 committed 48 days ago

Verified 770b7a3a

chore: clean wheel download directory and update path exclusions in test configurations (#1822)

chensuyue committed 48 days ago

Verified e46231bb

Support ByteDance-Seed/BAGEL-7B-MoT quantization in w4a16 format (#1633)

lvliang-intel committed 48 days ago

Verified 91679a5c

Scope ARK oneDNN XPU build, bump ARK version to 0.13.1, and remove the dpcpp runtime dependency (#1819)

Copilot committed 51 days ago

Verified a9f8fc1a

add smooth K for sagev1 (#1806)

luoyu-intel committed 51 days ago

Verified 017ed92c

chore: add shared agent config layout (#1700)

yiliu30 committed 52 days ago

Verified 8ccf34b0

[ARK CI] Enhance auto-round-lib CI test (#1801)

chensuyue committed 52 days ago

Verified 5bbe39ba

[refactor] decouple calibaration code (#1765)

n1ck-guo committed 52 days ago

Verified 71fb3506

reduce XPU memory usage in CI (#1812)

xin3he committed 52 days ago

Verified bc545633

set default DYNAMO_CACHE_SIZE_LIMIT to 16 (#1786)

wenhuach21 committed 53 days ago

Verified cb9b0b76

Add Dockerfile with torch installed, enhance image build logic to check for changes (#1811)

chensuyue committed 53 days ago

Verified 694ad39a

Fix mixed-precision accuracy regression when AutoScheme runs with CPU offloading and Hadamard rotation enabled (#1753)

lvliang-intel committed 53 days ago

Verified 65ae39e7

Fix GGUF-K RTN routing and fake eval dtype normalization (#1807)

n1ck-guo committed 53 days ago

Verified 351ba32a

Enhance ark test workflow (#1805)

chensuyue committed 53 days ago

Verified 72d7fc8a

Fix FP8 CT export metadata for KV cache and attention (#1752)

yiliu30 committed 54 days ago

Verified 24df42ea

fix bug of gguf alg ext (#1796)

n1ck-guo committed 54 days ago

Verified f64a0d5f

fix new arch bug for llmc (#1781)

n1ck-guo committed 54 days ago

Verified aa29325a

Integrate AutoRound Lib (#1723)

Zhenzhong1 committed 55 days ago

Verified 253117eb

support model_free WOQ quantization (#1699)

xin3he committed 55 days ago

Verified f0013f09

remove IPEX related code, doc, and test (#1787)

xin3he committed 55 days ago

Verified b2584b2d

add notes (#1795)

wenhuach21 committed 57 days ago

Verified 68df95b6

Fix incompatible weight names (#1759)

mengniwang95 committed 57 days ago

Verified 4c1eb8b1

fix amp (#1767)

wenhuach21 committed 58 days ago

Verified 6add4c27

fix amp (#1768)

wenhuach21 committed 58 days ago

Verified 8288c48f

fix accuracy regression and check it in CUDA CI (#1785)

xin3he committed 58 days ago

Verified 36767481

Optimize CUDA CI and Code Scan workflows (#1770)

XuehaoSun committed 58 days ago

Verified a46ad817

Older