Skip to content

Pull requests: intel/auto-round

New pull request New
22 Open 1,601 Closed
22 Open 1,601 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:reduce memory usage when loading native fused MoE checkpoints
#2382 opened Sep 18, 2026 by n1ck-guo Contributor Loading…
4 tasks
0.16.0
2
feat: implement optimized RTN toggle for NVFP4 E5M3 quantization and update CLI handling
#2376 opened Sep 17, 2026 by xin3he Contributor Loading…
4 tasks
0.16.0
7
feat: add mxfp8 mxfp4 moe bdpas prefill
#2371 opened Sep 16, 2026 by a32543254 Contributor Loading…
4 tasks
9
feat: use OpenS2V for diffusion calibration
#2368 opened Sep 16, 2026 by changwangss Contributor • Draft
2
refine dataset
#2363 opened Sep 15, 2026 by wenhuach21 Contributor Loading…
4 tasks
2
[Accuracy improvement] Re-implement opt-rtn for both imatrix and model-free, covering INT & NVFP
#2362 opened Sep 15, 2026 by xin3he Contributor • Draft
4 tasks
0.17.0
20
feat: multi-GPU quantization improvements -- batched device-local sea…
#2357 opened Sep 14, 2026 by avtc Collaborator Loading…
3 of 4 tasks
5
feat: data-parallel block tuning via --parallel_quantization
#2351 opened Sep 11, 2026 by avtc Collaborator • Draft
3 of 4 tasks
0.16.0
23
Refine device operations into a unified DeviceManager and ARDevice abstraction
#2344 opened Sep 11, 2026 by lvliang-intel Contributor Loading…
1 of 4 tasks
0.17.0
2
NeUQI grid search for optimized RTN (--enable_neuqi: joint asym scale/zp search, two-stage sym search, frozen-init anchor)
#2341 opened Sep 10, 2026 by avtc Collaborator Loading…
3 of 4 tasks
9
feat(ark): add INT4 S4 pre-packed Q*K kernel for SageAttention
#2319 opened Sep 8, 2026 by luoyu-intel Contributor • Draft
Enhance offload cleanup handling for exception cases
#2317 opened Sep 8, 2026 by lvliang-intel Contributor Loading…
1 of 4 tasks
8
Recurrent Residual Quantization (RRQ) for LLMs
#2308 opened Sep 6, 2026 by luoyu-intel Contributor Loading…
60
support teq algo experimental WIP
#2301 opened Sep 4, 2026 by WeiweiZhang1 Contributor Loading…
4 tasks
2
Xpu hmt mxfp4
#2264 opened Aug 31, 2026 by a32543254 Contributor • Draft
4 tasks
Add lagrangian solver in AutoScheme
#2221 opened Aug 24, 2026 by wenhuach21 Contributor Loading…
4 tasks
2
ark: add BF16/FP16 Sparge variants
#2145 opened Aug 11, 2026 by yiliu30 Contributor • Draft
4 tasks
0.16.0
feat: W4A8 ARK XPU MoE kernel (int4 weight / int8 compute) with prefill + decode
#2143 opened Aug 11, 2026 by Copilot AI Loading…
4 tasks done
@a32543254
48
Fix AutoRound gradients for Kimi-VL routed experts
#2097 opened Jul 28, 2026 by lesj0610 • Draft 0.16.0
2
Stream targeted block re-quantization's calibration pass
#2064 opened Jul 19, 2026 by aquilarubra Collaborator Loading… 0.16.0
18
Add hpu inference in CI test
#1976 opened Jul 1, 2026 by chensuyue Contributor Loading…
4 tasks
Add quantization support for DiffusionGemma
#1935 opened Jun 17, 2026 by lvliang-intel Contributor Loading…
1 of 4 tasks
23
ProTip! What’s not been updated in a month: updated:<2026-08-18.