Skip to content

Pull requests: intel/auto-round

New pull request New
24 Open 1,194 Closed
24 Open 1,194 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

Remove threaded packing from exporters
#1719 opened Apr 22, 2026 by yiliu30 Contributor Loading…
1
8
add support for MiMo-V2-Flash
#1718 opened Apr 22, 2026 by n1ck-guo Contributor Loading…
1 of 9 tasks
3
Reduce xpu memory usage with patch_xpu_sdpa_drop_causal_mask
#1716 opened Apr 21, 2026 by xin3he Contributor Loading…
2 of 9 tasks
9
feat: support Nemotron-H / Nemotron-Cascade-2 (#1711)
#1712 opened Apr 20, 2026 by michael-rabe • Draft
4 of 9 tasks
1
7
Add MLX format export support for Apple Silicon
#1706 opened Apr 19, 2026 by wenhuach Loading…
9 tasks
10
Continuously optimize AutoScheme RAM consumption
#1703 opened Apr 17, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
8
chore: add shared agent config layout
#1700 opened Apr 17, 2026 by yiliu30 Contributor Loading…
3
support model_free WOQ quantization
#1699 opened Apr 17, 2026 by xin3he Contributor Loading…
4 of 9 tasks
19
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
7
Fix module.to("meta") for models with plain Tensors
#1688 opened Apr 15, 2026 by yiliu30 Contributor Loading…
1 of 9 tasks
1
21
Security: HTTP requests are performed without timeout safeguards
#1683 opened Apr 15, 2026 by tomaioo Loading…
4
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
28
Refactor: use get_submodule with manual traversal fallback in get_module
#1677 opened Apr 13, 2026 by yael-shr Loading…
5 tasks done
1
fix gguf issue in alg_ext.py
#1649 opened Apr 2, 2026 by wenhuach21 Contributor Loading…
2 of 9 tasks
8
[Draft] Support TurboQuant KV-cache quantization
#1634 opened Mar 27, 2026 by lvliang-intel Contributor • Draft
2 of 9 tasks
3
Support ByteDance-Seed/BAGEL-7B-MoT quantization in w4a16 format
#1633 opened Mar 27, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
17
feat: add --dry-run estimation mode
#1592 opened Mar 22, 2026 by mvanhorn Loading…
1
6
Add Google-style docstrings to auto_round core modules and data_type/utils
#1559 opened Mar 18, 2026 by Copilot AI • Draft
4 of 9 tasks
@chensuyue
4
[Step1 ]new architecture for auto_round api/new engineering ready only add when the PR is ready to merge
#1542 opened Mar 13, 2026 by n1ck-guo Contributor Loading…
1 of 9 tasks
0.12.0
106
[N4Landing]update draft
#1538 opened Mar 12, 2026 by wenhuach21 Contributor Loading…
9 tasks
4
Enhance llmc CI on GPU and XPU
#1483 opened Mar 2, 2026 by chensuyue Contributor Loading…
1 of 9 tasks
0.13.0
14
Add asym for XPU backend. Stale
#1316 opened Jan 22, 2026 by luoyu-intel Contributor • Draft
1
[WIP][refactor quanizers][step 1] refactor rtn and tuning
#1278 opened Jan 14, 2026 by n1ck-guo Contributor Loading…
3
add per-task lm_eval args for exprimental usage Stale
#1017 opened Nov 11, 2025 by WeiweiZhang1 Contributor Loading…
1
ProTip! Follow long discussions with comments:>50.