Pull Requests intel/auto-round

Fix missing extra_config export for unsupported ignore_layers like `mlp.gate`

#1660 opened 2026-04-04 14:40 by lvliang-intel

fix autoscheme accuracy drop bug w/o low_gpu, add CI test

#1658 opened 2026-04-03 10:06 by WeiweiZhang1 0.12.1

try to support gemma4

#1656 opened 2026-04-03 07:50 by wenhuach21

add support for gemma4 model

#1655 opened 2026-04-03 07:25 by n1ck-guo

fix gguf issue in alg_ext.py

#1649 opened 2026-04-02 09:44 by wenhuach21

Enable low_cpu_mem_usage for mxfp/nvfp

#1648 opened 2026-04-02 08:26 by Kaihui-intel

support WOQ model input, such as kimi2.5

#1642 opened 2026-03-31 03:39 by xin3he

[not4landing]hadamard change

#1641 opened 2026-03-31 03:11 by wenhuach21

fix nextstep loading issue

#1640 opened 2026-03-30 12:59 by xin3he

[mllm] support longcat_next

#1637 opened 2026-03-30 06:28 by xin3he

[Draft] Support TurboQuant KV-cache quantization

#1634 opened 2026-03-27 13:28 by lvliang-intel

Support ByteDance-Seed/BAGEL-7B-MoT quantization in w4a16 format

#1633 opened 2026-03-27 12:44 by lvliang-intel

Support diffusion model AIDC-AI/Ovis-Image-7B quantization

#1616 opened 2026-03-25 12:50 by lvliang-intel

Enhance performance test

#1610 opened 2026-03-25 06:30 by XuehaoSun

feat: add --dry-run estimation mode

#1592 opened 2026-03-22 06:05 by mvanhorn

Refactor module access to use PyTorch get_submodule / set_submodule

#1590 opened 2026-03-20 15:32 by scopophobic

Add Google-style docstrings to auto_round core modules and data_type/utils

#1559 opened 2026-03-18 05:33 by Copilot

new architecture for auto_round api/new engineering

#1542 opened 2026-03-13 02:08 by n1ck-guo 0.12.0

[N4Landing]update draft

#1538 opened 2026-03-12 09:15 by wenhuach21

Enhance llmc CI on GPU and XPU

#1483 opened 2026-03-02 08:41 by chensuyue 0.13.0

Add asym for XPU backend.

#1316 opened 2026-01-22 03:39 by luoyu-intel

Robust FP8 layer detection for ignore_layers (#1283)

#1289 opened 2026-01-15 14:21 by scopophobic

Fix ignore_layers not working for FP8 models

#1286 opened 2026-01-15 04:15 by Copilot

[WIP][refactor quanizers][step 1] refactor rtn and tuning

#1278 opened 2026-01-14 08:52 by n1ck-guo

add per-task lm_eval args for exprimental usage Stale

#1017 opened 2025-11-11 07:22 by WeiweiZhang1