Skip to content

Pull requests: intel/auto-round

New pull request New
27 Open 1,159 Closed
27 Open 1,159 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

quick fix: gptqmodel no longer includes gptqmodel_marlin_kernels
#1671 opened Apr 9, 2026 by xin3he Contributor Loading…
1 of 9 tasks
3
Add compressed-tensors format export support for W4A16 and W8A16
#1669 opened Apr 9, 2026 by thuang6 Contributor Loading…
6 of 9 tasks
0.13.0
11
Fix omni model test CI issue
#1667 opened Apr 7, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
3
Support MXINT4 scheme
#1666 opened Apr 7, 2026 by mengniwang95 Contributor Loading…
1 of 6 tasks
fix hadamard transform weight dtype, using float32 as default and in-place transformed weight .
#1665 opened Apr 7, 2026 by lkk12014402 Contributor Loading…
7
[step 1]support variable block input shapes for gemma4
#1656 opened Apr 3, 2026 by wenhuach21 Contributor Loading…
2 of 9 tasks
13
add support for gemma4 model
#1655 opened Apr 3, 2026 by n1ck-guo Contributor Loading…
1 of 9 tasks
5
fix gguf issue in alg_ext.py
#1649 opened Apr 2, 2026 by wenhuach21 Contributor Loading…
9 tasks
2
Enable low_cpu_mem_usage for mxfp/nvfp
#1648 opened Apr 2, 2026 by Kaihui-intel Contributor Loading…
1 of 9 tasks
3
support WOQ model input, such as kimi2.5
#1642 opened Mar 31, 2026 by xin3he Contributor Loading…
9 tasks
8
inplace hadamard
#1641 opened Mar 31, 2026 by wenhuach21 Contributor • Draft
9 tasks
10
Enable NextStepDiffusion and support multi-device tuning for diffusion
#1640 opened Mar 30, 2026 by xin3he Contributor Loading…
9 tasks
14
[mllm] support longcat_next
#1637 opened Mar 30, 2026 by xin3he Contributor Loading…
1 of 9 tasks
10
[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
Support diffusion model AIDC-AI/Ovis-Image-7B quantization
#1616 opened Mar 25, 2026 by lvliang-intel Contributor Loading…
2 of 9 tasks
3
feat: add --dry-run estimation mode
#1592 opened Mar 22, 2026 by mvanhorn Loading…
1
6
Refactor module access to use PyTorch get_submodule / set_submodule
#1590 opened Mar 20, 2026 by scopophobic Contributor Loading…
11
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
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
73
[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.
#1316 opened Jan 22, 2026 by luoyu-intel Contributor • Draft
Robust FP8 layer detection for ignore_layers (#1283)
#1289 opened Jan 15, 2026 by scopophobic Contributor Loading…
3
Fix ignore_layers not working for FP8 models
#1286 opened Jan 15, 2026 by Copilot AI Loading…
11 tasks done
@yiliu30
8
ProTip! Adding no:label will show everything without a label.