intel/auto-round

Pull Requests Commits

yiliu30 committed 163 days ago

55ad84aa

yiliu30 committed 170 days ago

641e4f05

update mtp quant for special cases (#1691)

xin3he committed 171 days ago

Verified 89769e8a

rename scheme INT8_W8A8 to INT8 (#1687)

thuang6 committed 172 days ago

Verified 6a3bb90f

fix: add missing run_mllm entry point alias (#1695)

JGSphaela committed 174 days ago

Verified 693e4bd7

Add Claude skills for AutoRound (#1686)

lvliang-intel committed 174 days ago

Verified 4abe4067

Enable low_cpu_mem_usage for mxfp/nvfp (#1648)

Kaihui-intel committed 174 days ago

Verified 8d7bb84c

Gate large FP4 packing test by GPU memory (#1696)

yiliu30 committed 174 days ago

Verified a4dee986

support WOQ model input, such as kimi2.5 (#1642)

xin3he committed 175 days ago

Verified d5a0097d

Support diffusion model AIDC-AI/Ovis-Image-7B quantization (#1616)

lvliang-intel committed 175 days ago

Verified 95a84d2b

fp8_block bug fix (#1693)

mengniwang95 committed 175 days ago

Verified 42101801

reduce flux CUDA CI tuning memory from 30G to 5GB (#1694)

xin3he committed 175 days ago

Verified 751216a4

Fix hadamard transform weight dtype, using float32 as default and in-place transformed weight. (#1665)

lkk12014402 committed 175 days ago

Verified 43748dd9

Stabilize Qwen3-Omni MoE weight fidelity test for matching NaNs (#1681)

lvliang-intel committed 176 days ago

Verified 865f31b2

Enable NextStepDiffusion and support multi-device tuning for diffusion (#1640)

xin3he committed 177 days ago

Verified f81e20d6

Support MXINT4 scheme (#1666)

mengniwang95 committed 178 days ago

Verified c817d495

[mllm] support longcat_next (#1637)

xin3he committed 178 days ago

Verified 0821817b

Add compressed-tensors format export support for W4A16 and W8A16 (#1669)

thuang6 committed 178 days ago

Verified bbda38a6

Refactor module access to use PyTorch get_submodule / set_submodule (#1590)

scopophobic committed 181 days ago

Verified 58221b4a

Fix omni model test CI issue (#1667)

lvliang-intel committed 181 days ago

Verified bbda4046

Update unit test requirements (#1670)

XuehaoSun committed 182 days ago

Verified 440faaf1

Fix missing extra_config export for unsupported ignore_layers like `mlp.gate` (#1660)

lvliang-intel committed 182 days ago

Verified d2a62b89

import gptqmodel in confest to avoid error in transformers (#1668)

xin3he committed 183 days ago

Verified 106a3223

add gptqmodel 6.0 compatible change and MTP quantization skip warning. (#1663)

xin3he committed 184 days ago

Verified ac7aa288

fix autoscheme accuracy drop bug w/o low_gpu, add CI test (#1658)

WeiweiZhang1 committed 184 days ago

Verified c9a0d77b

Enhance performance test (#1610)

XuehaoSun committed 184 days ago

Verified 5b0d3faa

[pre-commit.ci] pre-commit autoupdate (#1661)

pre-commit-ci[bot] committed 184 days ago

Verified e4f94931

force auto-scheme low_gpu to True in CLI (#1653)

wenhuach21 committed 188 days ago

Verified 0f7dba7d

Correct docstring (#1652)

yiliu30 committed 188 days ago

Verified de0650e1

Enhance quantization configuration support for mixed precision and schemes in utils and tests (#1643)

xin3he committed 189 days ago

Verified 4632b2e9

Older