Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
20 Open 1,333 Closed
20 Open 1,333 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 guidance bug
#1988 opened Feb 24, 2026 by baijumeswani Loading…
Fix incorrect batch responses when using multiple prompts
#1986 opened Feb 23, 2026 by lnigam Loading…
3
[VitisAI] external_ep_libray support fix for WinML
#1984 opened Feb 19, 2026 by akholodnamdcom • Draft
Add model builder support for LFM2
#1979 opened Feb 14, 2026 by xenova Loading…
18
[Draft] Parakeet export
#1977 opened Feb 12, 2026 by jiafatom • Draft
9
remove one assert not verified with model microsoft/OptiMind-SFT
#1975 opened Feb 12, 2026 by xadupre Loading…
KV Cache optimization based on sequence length
#1974 opened Feb 11, 2026 by chilukam-qti Loading…
[DRAFT] Nemotron ASR Support
#1972 opened Feb 10, 2026 by nenad1002 • Draft
1
Support UpdatePositionIds in webgpu's interface
#1952 opened Jan 22, 2026 by qjia7 • Draft
3
Make phi model of webgpu ep always use long RoPE to improve tps performance for long context scenario
#1930 opened Dec 22, 2025 by feich-ms • Draft
3
Remove unused unit tests
#1923 opened Dec 17, 2025 by apsonawane Loading…
1
Update setup.py.in - rename the package and update install requires
#1912 opened Dec 9, 2025 by abalasa-amd • Draft
Also clear provider_options when ClearProviders is called
#1894 opened Nov 26, 2025 by Zhaeong Loading…
Enable GENAI with FetchContent or find_package() for client projects
#1858 opened Nov 9, 2025 by apwojcik Loading…
Change OpenVINO ep device selection priority
#1840 opened Oct 23, 2025 by chemwolf6922 Loading…
2
Support for decoder pipeline based multimodel
#1775 opened Sep 18, 2025 by prudhvi-qti • Draft
9
[WIP] Add TMAC quantization support for GPTQ model
#1703 opened Aug 25, 2025 by vraspar • Draft
[WIP] Add support for INT2 and UINT2 data types
#1643 opened Jul 21, 2025 by vraspar • Draft
Modify Model Builder to build paged attention models
#1605 opened Jul 3, 2025 by aciddelgado • Draft
9
add extra_options use_channel_wised_quantization to builder.py
#1362 opened Mar 31, 2025 by bopeng1234 Loading…
8
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.