Skip to content

Pull requests: intel/auto-round

New pull request New
34 Open 1,401 Closed
34 Open 1,401 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

add blockwise rotation.
#2087 opened Jul 24, 2026 by lkk12014402 Contributor Loading…
1
fix gguf format gemma4 High RAM and glm-4.7 error
#2084 opened Jul 23, 2026 by n1ck-guo Contributor Loading…
4 tasks
2
[Feature]: speedup autoscheme with multi-process and cache files
#2083 opened Jul 23, 2026 by xin3he Contributor Loading…
4 tasks
9
[WIP][Step2] refine alg
#2082 opened Jul 23, 2026 by wenhuach21 Contributor Loading…
4 tasks
6
perf: N-based tile selection for XPU bf16/fp16 MoE grouped GEMM
#2079 opened Jul 23, 2026 by Copilot AI • Draft
1 of 4 tasks
@a32543254
support fused MoE quantization and export for GGUF format
#2072 opened Jul 21, 2026 by n1ck-guo Contributor Loading…
4 tasks
2
feat: enable torch.compile by default and update related documentation
#2070 opened Jul 20, 2026 by xin3he Contributor Loading…
4 tasks
2
Allow non-MLLM calibration datasets when not quantizing vision
#2065 opened Jul 19, 2026 by aquilarubra Loading…
2
Stream targeted block re-quantization's calibration pass
#2064 opened Jul 19, 2026 by aquilarubra Loading…
Stream AutoScheme's per-layer sensitivity scoring block-by-block
#2063 opened Jul 19, 2026 by aquilarubra Loading…
6
Add crash/resume support for tuning runs (AR_RESUME_DIR)
#2062 opened Jul 19, 2026 by aquilarubra Loading…
Stream large checkpoints from disk during quantization
#2061 opened Jul 19, 2026 by aquilarubra Loading…
Refator UT and improve code coverage
#2057 opened Jul 16, 2026 by lvliang-intel Contributor • Draft
2 of 4 tasks
Decoupling oneDNN
#2049 opened Jul 13, 2026 by Zhenzhong1 Contributor Loading…
4 tasks done
24
feat: add per-head fp8 kv attention calibration
#2044 opened Jul 10, 2026 by zeel2104 Loading…
2 of 4 tasks
7
feat: Support world model Cosmos3
#2040 opened Jul 10, 2026 by lvliang-intel Contributor Loading…
3 of 4 tasks
6
fix the int4 ark test
#2038 opened Jul 10, 2026 by a32543254 Contributor Loading…
4 tasks
2
test: stabilize flaky int4-sym fp16 MoE prefill accuracy test
#2033 opened Jul 9, 2026 by Copilot AI • Draft
4 tasks done
@a32543254
44
[WIP]refine quantizer
#2031 opened Jul 9, 2026 by wenhuach21 Contributor Loading…
4 tasks
1
Enhance CI pipeline and unit tests for AI failure analysis WIP
#2029 opened Jul 9, 2026 by chensuyue Contributor Loading…
ark: add SpargeAttn support
#2027 opened Jul 8, 2026 by yiliu30 Contributor Loading…
12
Implementing bandwidth metrics for performance tests
#2020 opened Jul 8, 2026 by Copilot AI • Draft
@a32543254
1
refactor scheme,layer_config and formats
#2013 opened Jul 7, 2026 by n1ck-guo Contributor Loading…
4 tasks
2
update auto_scheme_acc doc
#2000 opened Jul 6, 2026 by n1ck-guo Contributor Loading…
4 tasks
2
fix: replace bare except clauses with except Exception
#1981 opened Jul 1, 2026 by ramkrishs Contributor Loading…
4 of 5 tasks
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.