Pull Requests intel/auto-round

Robust FP8 layer detection for ignore_layers (#1283)

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

fix low_cpu new

#1288 opened 2026-01-15 07:00 by wenhuach21

fix bug of format

#1287 opened 2026-01-15 05:05 by n1ck-guo

Fix ignore_layers not working for FP8 models

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

Preserve FP8 format for ignored layers in FP8 models

#1285 opened 2026-01-15 04:11 by Copilot

Update version

#1282 opened 2026-01-15 02:39 by XuehaoSun

Fix fp_layers kwarg forwarded as ignore instead of ignore_layers

#1281 opened 2026-01-15 01:37 by Copilot

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

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

refine low_cpu

#1270 opened 2026-01-13 07:59 by wenhuach21

refine moe modellings to reduce peak ram usage

#1265 opened 2026-01-13 06:46 by WeiweiZhang1

fix XPU CI hang issue

#1261 opened 2026-01-12 11:10 by xin3he

(feat): add support for g2 fp8 on cpu with LUT

#1254 opened 2026-01-10 11:19 by SwekeR-463

Fix low cpu

#1253 opened 2026-01-09 11:12 by wenhuach21

fix disable_opt_rtn spelling error

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

extend compatible test

#1131 opened 2025-12-12 02:50 by chensuyue

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