Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
24 Open 1,251 Closed
24 Open 1,251 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 processor for QWen 2.5 VL
#1891 opened Nov 25, 2025 by tianleiwu • Draft
Support pre-registered plug-in NvTensorRtRtx execution provider library
#1889 opened Nov 24, 2025 by anujj Loading…
2
Fix bug in Squeeze for getting the value of total_seq_len
#1886 opened Nov 21, 2025 by Honry Loading…
9
Generic shared emb_tokens/lm_head implementation
#1885 opened Nov 20, 2025 by jixiongdeng Loading…
29
Add model builder for Qwen2_5_VLTextModel
#1882 opened Nov 19, 2025 by tianleiwu Loading…
33
Bump torch from 2.7.1 to 2.7.1+cpu in /test/python/directml/torch dependencies Pull requests that update a dependency file python Pull requests that update python code
#1868 opened Nov 13, 2025 by dependabot bot Loading…
Fix gpt-oss model export
#1861 opened Nov 11, 2025 by apsonawane Loading…
5
Add linker flags for 16 KB page size on Android
#1860 opened Nov 11, 2025 by sheetalarkadam Loading…
Enable GENAI with FetchContent or find_package() for client projects
#1858 opened Nov 9, 2025 by apwojcik Loading…
whisper: Support a variant of the whisper pipeline where encoder / decoder are stateful.
#1857 opened Nov 7, 2025 by RyanMetcalfeInt8 Loading…
4
C# binding into STFT pre-processing
#1843 opened Oct 27, 2025 by nenad1002 Loading…
26
Change OpenVINO ep device selection priority
#1840 opened Oct 23, 2025 by chemwolf6922 Loading…
2
Add Android 16KB page size support for Google Play compliance
#1810 opened Oct 9, 2025 by Copilot AI • Draft
7 tasks done
4
Only manually load DLLs if onnxruntime.dll is not already loaded.
#1800 opened Sep 30, 2025 by chemwolf6922 Loading…
2
Add Gemma-3 vision tutorial to ONNX Runtime GenAI
#1793 opened Sep 25, 2025 by kunal-vaishnavi Loading…
4
Support for decoder pipeline based multimodel
#1775 opened Sep 18, 2025 by prudhvi-qti • Draft
9
Update ThirdPartyNotice.txt
#1764 opened Sep 16, 2025 by anujj Loading…
1
[Need discussion] Add graph capture for webgpu
#1720 opened Sep 3, 2025 by qjia7 • Draft
1
[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
[DO NOT MERGE] Use fp16 GQA in cuda-fp32 conversion
#1613 opened Jul 8, 2025 by jiafatom Loading…
Modify Model Builder to build paged attention models
#1605 opened Jul 3, 2025 by aciddelgado • Draft
9
[WIP]Stable Diffusion in GenAI
#1478 opened May 13, 2025 by selenayang888 • Draft
1
add extra_options use_channel_wised_quantization to builder.py
#1362 opened Mar 31, 2025 by bopeng1234 Loading…
8
ProTip! Filter pull requests by the default branch with base:main.