Pull Requests intel/auto-round

fix dynamic int8 w8a8 export issue with tuning

#1525 opened 2026-03-10 04:02 by thuang6

support hadamard transform for mxfp4/nvfp4 with rtn or autoround method

#1515 opened 2026-03-09 03:03 by lkk12014402 0.12.0

Support GLM-Image model quantizaiton

#1512 opened 2026-03-08 13:24 by lvliang-intel

Fix #1284: preserve FP8 format for layers specified in ignore_layers

#1511 opened 2026-03-08 02:11 by LuciferDono

Support block-wise fp8 quant

#1487 opened 2026-03-03 05:44 by mengniwang95

Enhance llmc CI on GPU and XPU

#1483 opened 2026-03-02 08:41 by chensuyue 0.12.0

Enable CUDA CI

#1473 opened 2026-02-27 02:55 by XuehaoSun 0.12.0

Support Qwen3 and Qwen2.5 Omni model quantization

#1404 opened 2026-02-04 14:48 by lvliang-intel

[Experimental][Won't Merge] DDP PoC won't merge

#1391 opened 2026-02-04 01:47 by yiliu30

Refactor module access to use PyTorch get/set_submodule API

#1365 opened 2026-01-29 05:39 by scopophobic

support hadamard transform for mxfp4 with rtn or autoround method.

#1349 opened 2026-01-27 05:20 by lkk12014402

refactor init of compressor engineering ready

#1339 opened 2026-01-26 03:04 by n1ck-guo

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

fix disable_opt_rtn spelling error

#1250 opened 2026-01-09 02:19 by WeiweiZhang1

add per-task lm_eval args for exprimental usage

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

[WIP] [STEP 2] split compressor into few quantizers

#841 opened 2025-09-23 00:25 by n1ck-guo