Skip to content

Pull requests: intel/auto-round

New pull request New
26 Open 1,252 Closed
26 Open 1,252 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix merge error of llmc bug
#1817 opened May 14, 2026 by n1ck-guo Contributor Loading…
4 tasks
7
Fix forwarding of ExtraConfig overrides
#1816 opened May 14, 2026 by dhruvil237 Loading…
2 of 4 tasks
0.13.0
2
Add XPU MoE decode kernel (FP16/BF16 + INT4 sym/asym)
#1813 opened May 14, 2026 by Copilot AI • Draft
7 tasks done
@a32543254
add mimo-audio, Qwen-TTS model backbone quantization
#1810 opened May 13, 2026 by WeiweiZhang1 Contributor Loading…
4 tasks
0.13.0
21
[bug fix] model free: fix copy folder of diffusion model, fix unresponsive disable_model_free, and cuda UT
#1809 opened May 13, 2026 by xin3he Contributor Loading…
3 of 4 tasks
0.13.0
14
add auto_round_rtn cli and remove fast
#1808 opened May 13, 2026 by n1ck-guo Contributor Loading…
4 tasks
0.13.0
11
add smooth K for sagev1
#1806 opened May 13, 2026 by luoyu-intel Contributor Loading…
6
Integrate vLLM loading support into AutoRound new architecture
#1804 opened May 12, 2026 by changwangss Loading…
4 tasks
0.13.0
31
support AR format FP8 in vLLM
#1798 opened May 11, 2026 by Zhenzhong1 Contributor Loading…
7
support quarot/spinquant rotation before quantization
#1797 opened May 11, 2026 by lkk12014402 Contributor Loading… 0.13.0
18
Reduce RAM usage of quantizing VLM models and fix some issues of quantizing gemma4
#1791 opened May 9, 2026 by lvliang-intel Contributor Loading…
1 of 4 tasks
0.13.0
28
Refine device by vibecoding
#1790 opened May 8, 2026 by wenhuach21 Contributor Loading…
4 tasks
7
Reduce VRAM usage of quantizing VLM models
#1777 opened May 4, 2026 by lvliang-intel Contributor Loading…
1 of 4 tasks
0.13.0
10
Fix QDQ inference OOM issue.
#1763 opened Apr 29, 2026 by changwangss Loading…
4
Awq algorithm
#1749 opened Apr 28, 2026 by WeiweiZhang1 Contributor Loading…
3 of 4 tasks
0.13.0
27
fix qwen3.6 vllm infer bug ready only add when the PR is ready to merge
#1746 opened Apr 27, 2026 by n1ck-guo Contributor Loading…
4 tasks
0.13.0
6
Fix rotation
#1724 opened Apr 23, 2026 by wenhuach21 Contributor Loading…
2 of 9 tasks
14
feat: support Nemotron-H / Nemotron-Cascade-2 (#1711)
#1712 opened Apr 20, 2026 by michael-rabe Loading…
4 of 9 tasks
1
8
Continuously optimize AutoScheme RAM consumption
#1703 opened Apr 17, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
12
chore: add shared agent config layout
#1700 opened Apr 17, 2026 by yiliu30 Contributor Loading…
4
Fix Qwen Omni quantization model issue for long form audio generation
#1698 opened Apr 17, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
13
Security: HTTP requests are performed without timeout safeguards
#1683 opened Apr 15, 2026 by tomaioo Loading… 0.13.0
5
Feats: Quantize/save/evaluate the Wan-AI/WAN2.2 models in w4a16 format
#1678 opened Apr 14, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
36
Refactor: use get_submodule with manual traversal fallback in get_module
#1677 opened Apr 13, 2026 by yael-shr Loading…
5 tasks done
1
refine alg_ext code to better support torch compile
#1649 opened Apr 2, 2026 by wenhuach21 Contributor Loading…
2 of 9 tasks
0.13.0
16
ProTip! Filter pull requests by the default branch with base:main.