intel/auto-round

Pull Requests Commits

Fix requirements packaging for source distribution (#1455)

timkpaine committed 264 days ago

Verified c0dc55fc

[Regression] fix FP8_STATIC loading (#1452)

xin3he committed 265 days ago

Verified 9855b4ba

Attach `act_max_hook` for FP8 model (#1447)

yiliu30 committed 266 days ago

Verified 81c8ee42

bump version (#1445)

chensuyue committed 266 days ago

Verified 0f087c91

fix bug of evaluate_accuracy (#1430)

xin3he committed 266 days ago

Verified 40253afe

update readme for Intel xpu usage (#1441)

chensuyue committed 266 days ago

Verified f16d57d7

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

xin3he committed 266 days ago

Verified 86231c44

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

chensuyue committed 266 days ago

Verified 232b1da9

Enable new cpu test pool (#1435)

chensuyue committed 267 days ago

Verified 0c7f4af3

Update diffusion README (#1439)

mengniwang95 committed 267 days ago

Verified 6e786c90

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

xin3he committed 267 days ago

Verified 8a3d7937

refine global scale calculation to blockwise (#1421)

WeiweiZhang1 committed 267 days ago

Verified a554a107

fix CUDA CI (#1431)

xin3he committed 267 days ago

Verified d0f3cd0e

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

xin3he committed 268 days ago

Verified a1876107

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

Kaihui-intel committed 268 days ago

Verified 16a18d7c

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

xin3he committed 268 days ago

Verified 319da040

fix bug in PR-1244 (#1422)

xin3he committed 268 days ago

Verified 81383e92

Refactor evaluation in tests to use evaluate_accuracy function (#1402)

xin3he committed 269 days ago

Verified 70a6bcc2

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

xin3he committed 269 days ago

Verified ebb534a2

fix test_evaluation and AutoTuner new issue (#1417)

xin3he committed 269 days ago

Verified 520214a8

Update torch to 2.9.1 in CI (#1313)

XuehaoSun committed 270 days ago

Verified 0cac8490

adapt vllm_ext to new extra config (#1409)

mengniwang95 committed 270 days ago

Verified d2b1fed1

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

chensuyue committed 272 days ago

Verified bab09935

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

xin3he committed 272 days ago

Verified 6093abc2

refine qwen3_vl_moe experts forward (#1413)

WeiweiZhang1 committed 272 days ago

Verified 2824c37b

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

WeiweiZhang1 committed 272 days ago

Verified 40bd6410

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

n1ck-guo committed 273 days ago

Verified 96cfbc95

[LLMC] Wrap block for DDP (#1407)

yiliu30 committed 273 days ago

Verified 99204417

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

xin3he committed 273 days ago

Verified b2bf11df

Enable xpu test for CI (#1352)

chensuyue committed 273 days ago

Verified 4bcebe7a

Older