Skip to content

Pull requests: microsoft/Olive

New pull request New
28 Open 2,228 Closed
28 Open 2,228 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

Bump cryptography from 48.0.1 to 50.0.0 in /mcp dependencies Pull requests that update a dependency file python:uv Pull requests that update python:uv code
#2606 opened Aug 4, 2026 by dependabot Bot Loading…
2
Test/unit suite acceleration
#2605 opened Aug 4, 2026 by xiaoyu-work Collaborator Loading…
5 tasks
15
Improve olive skill recipe inference
#2603 opened Aug 4, 2026 by xiaoyu-work Collaborator Loading…
5 tasks
5
Emit ORT-spec-compliant model packages from generate-model-package
#2602 opened Aug 3, 2026 by xiaoyu-work Collaborator Loading…
5 tasks
2
Fix test_mnb_to_qdq for ORT versions that fixed the int4→uint8 DQ bug
#2595 opened Jul 30, 2026 by Copilot AI Loading…
5 tasks
1
@xadupre
12
Make accessing and gathering search results easier
#2591 opened Jul 29, 2026 by shaahji Collaborator Loading…
3 of 5 tasks
18
add discrepancies for whisper models
#2590 opened Jul 29, 2026 by xadupre Member • Draft
6
Fix HQQ MatMulNBits weight layout
#2589 opened Jul 28, 2026 by DelwinKim Loading…
4 of 5 tasks
7
Fix OnnxDiscrepancyCheck crash on BF16 models — format_data cannot convert bfloat16 to NumPy
#2585 opened Jul 23, 2026 by tadani3 Contributor Loading…
3 of 5 tasks
@tadani3
5
Extend PyTorch RTN weight quantization to MoE experts
#2584 opened Jul 21, 2026 by Copilot AI Loading…
2
@titaiwangms
9
add fast test to check with bfloat16
#2581 opened Jul 21, 2026 by xadupre Member Loading…
30
Olive QAIRT model provenance initial
#2578 opened Jul 20, 2026 by qti-kromero Contributor Loading…
5 tasks done
21
New CLI command: search
#2576 opened Jul 17, 2026 by shaahji Collaborator • Draft
3 of 5 tasks
7
Migrate bnb4, io_datatype_converter, dynamic_to_fixed_shape, and static_llm passes to onnx_ir
#2563 opened Jul 6, 2026 by justinchuby Contributor Loading…
3 of 5 tasks
37
Replace onnxruntime.tools.symbolic_shape_infer with onnx-shape-inference
#2562 opened Jul 6, 2026 by Copilot AI • Draft
2 of 5 tasks
1
@justinchuby
3
Reuse quantized embedding table for tied LM head in TieWordEmbeddings
#2549 opened Jul 1, 2026 by justinchuby Contributor Loading…
4 of 5 tasks
4
Add QairtModelHandler input support to QairtPipelinePass
#2545 opened Jun 25, 2026 by qti-kromero Contributor • Draft
5 tasks
1
Remove ort pin for gpu ci
#2537 opened Jun 22, 2026 by xiaoyu-work Collaborator • Draft
5 tasks
2
Add multimodal evaluation and component-aware quantization support
#2531 opened Jun 19, 2026 by DelwinKim • Draft
4 tasks done
34
COPY of #2486
#2512 opened Jun 10, 2026 by shaahji Collaborator • Draft
5 tasks
Add OnnxMoEQuantization pass (com.microsoft::MoE → QMoE)
#2491 opened Jun 1, 2026 by justinchuby Contributor • Draft
6
fix: copy_dir leaks ignore_errors kwarg to shutil.copytree
#2486 opened Jun 1, 2026 by anisia19 Loading…
2 tasks done
10
Add multi build support
#2480 opened May 29, 2026 by xiaoyu-work Collaborator Loading…
34
feat: add components_to_skip to OnnxBlockWiseRtnQuantization
#2457 opened May 8, 2026 by titaiwangms Contributor Loading…
8
feat: add components_to_export filter to MobiusBuilder pass
#2456 opened May 8, 2026 by titaiwangms Contributor Loading…
11
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.