intel/auto-round

Pull Requests Commits

Merge branch 'main' into lvl/autoscheme_ram_opt

lvliang-intel committed 129 days ago

Verified 07e784b7

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

yiliu30 committed 130 days ago

Verified 24df42ea

Merge branch 'main' into lvl/autoscheme_ram_opt

lvliang-intel committed 130 days ago

Verified 410a4e41

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 130 days ago

a15b8250

Continue optimizing AutoScheme RAM consumption

lvliang-intel committed 130 days ago

976f90db

fix bug of gguf alg ext (#1796)

n1ck-guo committed 130 days ago

330bd78e

fix new arch bug for llmc (#1781)

n1ck-guo committed 130 days ago

bd935e4a

Integrate AutoRound Lib (#1723)

Zhenzhong1 committed 130 days ago

82a7b99b

support model_free WOQ quantization (#1699)

xin3he committed 130 days ago

a7d01a27

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

xin3he committed 130 days ago

4c77a982

add notes (#1795)

wenhuach21 committed 130 days ago

1295774e

Fix incompatible weight names (#1759)

mengniwang95 committed 130 days ago

a97e3342

fix amp (#1767)

wenhuach21 committed 130 days ago

75325d23

fix amp (#1768)

wenhuach21 committed 130 days ago

2b475833

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

xin3he committed 130 days ago

85733088

Optimize CUDA CI and Code Scan workflows (#1770)

XuehaoSun committed 130 days ago

f5189565

support gptqmodel 7.0.0 and fix bug in CI (#1772)

xin3he committed 130 days ago

66ed80da

clean and fix for new arch (#1761)

n1ck-guo committed 130 days ago

74594eb1

[MTP]split gate_up_proj and fix accu gap in rtn quantization (#1758)

xin3he committed 130 days ago

4d991746

Fix hpu error (#1766)

n1ck-guo committed 130 days ago

9324bdf2

delete unreproduced results for now (#1760)

ZaneMark committed 130 days ago

d9e0f6ad

Fix vllm CUDA CI (#1750)

XuehaoSun committed 130 days ago

c3690709

New architecture for auto_round (#1542)

n1ck-guo committed 130 days ago

38ef9463

add support for MiMo-V2-Flash (#1718)

n1ck-guo committed 130 days ago

a4f9bf9f

add warnings for lm_head activation scale fallback (#1728)

n1ck-guo committed 130 days ago

cc66be71

[Experimental]Add MLX format export support and AutoScheme for vlm support (#1732)

wenhuach21 committed 130 days ago

145847b1

Reduce xpu memory usage with patch_xpu_sdpa_drop_causal_mask (#1716)

xin3he committed 130 days ago

4c2238fd

Enhance llmc CI on XPU (#1483)

chensuyue committed 130 days ago

8bced5f7

add small zimage test and fix bug (#1734)

xin3he committed 130 days ago

26c75743

Remove threaded packing from exporters (#1719)

yiliu30 committed 130 days ago

1643ce1a

Older