Pull Requests intel/auto-round

refactor and support for multi algs fusion enhancement api/new ready

#1920 opened 2026-06-13 01:22 by n1ck-guo

Refine AutoScheme logic for gguf, reduce memory consumption and improve speed

#1916 opened 2026-06-11 09:05 by wenhuach21

[draft]refine device

#1900 opened 2026-06-09 07:40 by wenhuach21

DDP for multiple cards

#1897 opened 2026-06-09 01:09 by yiliu30

add mxfp support for awq WIP experimental

#1892 opened 2026-06-05 08:05 by WeiweiZhang1

feat: add overlap function for multi-blocks compression

#1850 opened 2026-05-25 06:18 by ZaneMark

Add quantized MoE prefill kernel for XPU (stage-1 functional baseline)

#1813 opened 2026-05-14 04:27 by Copilot

Fix QDQ inference OOM issue.

#1763 opened 2026-04-29 05:50 by changwangss

feat: support Nemotron-H / Nemotron-Cascade-2 (#1711)

#1712 opened 2026-04-20 18:41 by michael-rabe

Continuously optimize AutoScheme RAM consumption

#1703 opened 2026-04-17 05:43 by lvliang-intel

Refactor: use get_submodule with manual traversal fallback in get_module

#1677 opened 2026-04-13 14:04 by yael-shr