intel/auto-round

Pull Requests Commits

XuehaoSun committed 1 day ago

Verified 8f346981

Fix requirements packaging for source distribution (#1455)

timkpaine committed 1 day ago

Verified c56e8c0d

bump version to v0.10.1

chensuyue committed 12 days ago

bc32a5a9

[Regression] fix FP8_STATIC loading (#1452) (#1453)

chensuyue committed 12 days ago

Verified 97773b2d

add test trigger

chensuyue committed 12 days ago

2120f166

chensuyue committed 13 days ago

1f02a087

update readme for Intel xpu usage (#1441)

chensuyue committed 13 days ago

e730ef42

update logic for compatibility with gptqmodel:exllamav2 backend (#1438)

xin3he committed 13 days ago

41943610

Update auto-round-lib README.md (#1437)

chensuyue committed 13 days ago

2664adcb

Enable new cpu test pool (#1435)

chensuyue committed 13 days ago

ef89b819

Update diffusion README (#1439)

mengniwang95 committed 13 days ago

7c9e8bb6

support GPTQ_FORMAT for "gptqmodel:exllamav2" backend (#1434)

xin3he committed 14 days ago

3dacfaf3

fix CUDA CI (#1431)

xin3he committed 14 days ago

e37f7271

Update BackendInfos for AutoGPTQ based on transformer version and save g_idx for gptqmodel backend (#1429)

xin3he committed 15 days ago

c0350337

Fix cuda model ut [glm4][Molmo] (#1428)

Kaihui-intel committed 15 days ago

bb767cf4

remove require_intel_extension_for_pytorch and fix TypeError: unhashable type: 'set' (#1425)

xin3he committed 15 days ago

5ab1306d

fix bug in PR-1244 (#1422)

xin3he committed 15 days ago

14ace03a

fix: update cleanup logic for quantized model path in tests (#1419)

xin3he committed 16 days ago

Verified ebb534a2

fix test_evaluation and AutoTuner new issue (#1417)

xin3he committed 16 days ago

Verified 520214a8

Update torch to 2.9.1 in CI (#1313)

XuehaoSun committed 16 days ago

Verified 0cac8490

adapt vllm_ext to new extra config (#1409)

mengniwang95 committed 16 days ago

Verified d2b1fed1

update auto-round-kernel package name to auto-round-lib (#1410)

chensuyue committed 19 days ago

Verified bab09935

[fix]AttributeError: 'Autotuner' object has no attribute '_cache_lock' (#1414)

xin3he committed 19 days ago

Verified 6093abc2

refine qwen3_vl_moe experts forward (#1413)

WeiweiZhang1 committed 19 days ago

Verified 2824c37b

fix Qwen3-VL model auto_awq export, add auto_awq vllm ut (#1384)

WeiweiZhang1 committed 19 days ago

Verified 40bd6410

better warning for not support mllm while quant_non_text_module (#1411)

n1ck-guo committed 19 days ago

Verified 96cfbc95

[LLMC] Wrap block for DDP (#1407)

yiliu30 committed 20 days ago

Verified 99204417

fix: update model imports from AutoModelForVision2Seq to AutoModelFor… (#1412)

xin3he committed 20 days ago

Verified b2bf11df

Enable xpu test for CI (#1352)

chensuyue committed 20 days ago

Verified 4bcebe7a

fix cuda ut fail: gptqmodel and gguf format with fp8 input model (#1399)

n1ck-guo committed 20 days ago

Verified 4dc04f4b

Older