Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
17 Open 1,145 Closed
17 Open 1,145 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

Generate pyd type info
#1742 opened Sep 9, 2025 by chemwolf6922 Loading…
1
Add TRT_RTX support for onnxruntime-genai-trt-rtx wheel
#1736 opened Sep 8, 2025 by anujj • Draft
2
[CUDA] sampling kernel improvements
#1732 opened Sep 6, 2025 by tianleiwu Loading…
44
[Don't review] Add graph capture for webgpu
#1720 opened Sep 3, 2025 by qjia7 • Draft
Provide distributed version of improved TopK kernel
#1710 opened Aug 27, 2025 by hariharans29 Loading…
19
[DO NOT MERGE] Improve TopK CUDA execution path while sampling and when vocab size is sufficiently large
#1705 opened Aug 26, 2025 by hariharans29 Loading…
13
[WIP] Add TMAC quantization support for GPTQ model
#1703 opened Aug 25, 2025 by vraspar • Draft
Add cpu path for gpt-oss model
#1700 opened Aug 25, 2025 by apsonawane • Draft
1
Add support for inference using EP context model
#1691 opened Aug 19, 2025 by thevishalagarwal Loading…
19
Introduce support for dynamic batching
#1662 opened Jul 29, 2025 by baijumeswani Loading…
[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
Fix KV cache handling for TensorRT execution provider when in place kv is disable
#1604 opened Jul 3, 2025 by anujj • Draft
[WIP]Stable Diffusion in GenAI
#1478 opened May 13, 2025 by selenayang888 • Draft
add extra_options use_channel_wised_quantization to builder.py
#1362 opened Mar 31, 2025 by bopeng1234 Loading…
8
Make Microsoft.ML.OnnxRuntimeGenAI.Tokenizer a Microsoft.ML.Tokenizers.Tokenizer
#970 opened Oct 11, 2024 by stephentoub Loading…
15
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.