ONNX Runtime GenAI
Project Links
Meta
Author: Microsoft Corporation
Classifiers
ONNX Runtime GenAI
Run SLMs/LLMs and multi-modal models on-device and in the cloud with ONNX Runtime.
For more details, see: docs https://onnxruntime.ai/docs/genai and repo: https://github.com/microsoft/onnxruntime-genai
0.15.0
Jul 30, 2026
0.14.1
Jun 02, 2026
0.14.0
May 26, 2026
0.13.2
May 01, 2026
0.13.1
Apr 07, 2026
0.13.0
Apr 05, 2026
0.12.2
Mar 04, 2026
0.12.1
Feb 24, 2026
0.12.0
Feb 13, 2026
0.11.4
Dec 12, 2025
0.11.3
Dec 08, 2025
0.11.2
Nov 18, 2025
0.11.1
Nov 16, 2025
0.11.0
Nov 14, 2025
0.10.0
Oct 10, 2025
0.9.2
Sep 16, 2025
0.9.1
Sep 09, 2025
0.9.0
Aug 06, 2025
0.8.3
Jun 30, 2025
0.8.2
Jun 05, 2025
0.8.1
May 30, 2025
0.8.0
May 17, 2025
0.7.1
Apr 21, 2025
0.7.0
Mar 28, 2025
0.7.0rc2
Mar 14, 2025
0.7.0rc1
Feb 27, 2025
0.6.0
Feb 14, 2025
0.6.0rc4
Feb 04, 2025
0.6.0rc3
Feb 04, 2025
0.6.0rc1
Jan 13, 2025
0.5.2
Nov 25, 2024
0.5.1
Nov 13, 2024
0.5.0
Nov 07, 2024
0.4.0
Aug 21, 2024
Wheel compatibility matrix
| Platform | CPython 3.11 | CPython 3.12 | CPython 3.13 | CPython 3.14 |
|---|---|---|---|---|
| manylinux_2_28_x86_64 | ||||
| win_amd64 | ||||
| win_arm64 |
Files in release
onnxruntime_genai_cuda-0.15.0-cp311-cp311-manylinux_2_28_x86_64.whl (17.3MiB)
onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_amd64.whl (9.9MiB)
onnxruntime_genai_cuda-0.15.0-cp311-cp311-win_arm64.whl (7.7MiB)
onnxruntime_genai_cuda-0.15.0-cp312-cp312-manylinux_2_28_x86_64.whl (17.3MiB)
onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_amd64.whl (9.9MiB)
onnxruntime_genai_cuda-0.15.0-cp312-cp312-win_arm64.whl (7.7MiB)
onnxruntime_genai_cuda-0.15.0-cp313-cp313-manylinux_2_28_x86_64.whl (17.3MiB)
onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_amd64.whl (9.9MiB)
onnxruntime_genai_cuda-0.15.0-cp313-cp313-win_arm64.whl (7.7MiB)
onnxruntime_genai_cuda-0.15.0-cp314-cp314-manylinux_2_28_x86_64.whl (17.3MiB)
onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_amd64.whl (10.0MiB)
onnxruntime_genai_cuda-0.15.0-cp314-cp314-win_arm64.whl (7.8MiB)