intel/auto-round

Pull Requests Commits

Merge branch 'main' into feature/overlap_for_nblocks

ZaneMark committed 124 days ago

Verified 4094962c

[ARK] Add varlen support for sdpa and update tests (#1957)

luoyu-intel committed 124 days ago

Verified 948c7783

Merge branch 'main' into feature/overlap_for_nblocks

ZaneMark committed 124 days ago

Verified 09eb1d3a

feat: add overlap function for multi-blocks compression

ZaneMark committed 124 days ago

bceb9b80

Adapt the latest sglang integration test Engine kwargs. (#1964)

changwangss committed 125 days ago

Verified 49244549

fix auto_scheme gguf format wrong bits if use tiny model (#1953)

n1ck-guo committed 125 days ago

Verified b1a6baf9

speed up awq ci (#1954)

WeiweiZhang1 committed 128 days ago

Verified 9468e52c

add other non-integer scheme support for awq (#1892)

WeiweiZhang1 committed 129 days ago

Verified 5a3ade8c

Remove kernels version limit in test (#1945)

chensuyue committed 129 days ago

Verified 142e91b4

Use shared tokenizer save helper in exporters (#1951)

changwangss committed 129 days ago

Verified 436b9db6

update ARK README (#1922)

luoyu-intel committed 129 days ago

Verified f42a0421

Implement shard parallelism configuration and update documentation (#1942)

xin3he committed 130 days ago

Verified 7e2b69d4

fix saving hadamard rotation model without rotation config. (#1933)

lkk12014402 committed 130 days ago

Verified 6a2e5ad3

fix few gguf bugs of hf-name and checkpoint name (#1939)

n1ck-guo committed 131 days ago

Verified 126793d5

Add flashinfer-jit-cache installation to cuda unit test setup (#1947)

XuehaoSun committed 131 days ago

Verified 349b0418

fix issue of step3p7 and CI failure (#1929)

xin3he committed 131 days ago

Verified 1c4baa03

Update PyTorch and torchvision versions to 2.12.1 and 0.27.1 in CI (#1943)

XuehaoSun committed 131 days ago

Verified 354c6a3b

Update CPU agent pool (#1936)

chensuyue committed 131 days ago

Verified 35650a09

Fix SIGSEGV in pack-weight unpack/GEMM on malformed blob (#1928)

luoyu-intel committed 132 days ago

Verified 495e2539

Refine AutoScheme logic for gguf, reduce memory consumption and improve speed (#1916)

wenhuach21 committed 132 days ago

Verified 0c9c5b1d

DDP for multiple cards (#1897)

yiliu30 committed 134 days ago

Verified 33b7df0e

reorder UT for CUDA CI memory leak (#1938)

xin3he committed 136 days ago

Verified 0cc47c69

update what's new: vllm-omni integrates AutoROund (#1931)

xin3he committed 136 days ago

Verified 759a9ad7

Enhance b70 check (#1937)

yiliu30 committed 136 days ago

Verified e8709167

Support Wan2.2 S2V Quantization (#1924)

changwangss committed 136 days ago

Verified ca378799

Fix UT coverage (#1927)

XuehaoSun committed 136 days ago

Verified 6b311875

[Model Free] Add MXFP mix-precision quantization and support RoutedExperts (#1921)

xin3he committed 137 days ago

Verified be043f32

refactor and support for multi algs fusion (#1920)

n1ck-guo committed 137 days ago

Verified df9299da

enable MXFP clamp for model free (#1914)

xin3he committed 142 days ago

Verified 50ee58c9

fix awq cuda CI (#1912)

WeiweiZhang1 committed 143 days ago

Verified 34790de7

Older