microsoft/onnxruntime-genai v0.10.0
microsoft/onnxruntime-genai
Captured source
source ↗published Oct 10, 2025seen Jun 26captured 5dhttp 200method plain
v0.10.0
Repository: microsoft/onnxruntime-genai
Tag: v0.10.0
Published: 2025-10-10T17:26:47Z
Prerelease: no
Release notes:
What's Changed
- Enable continuous decoding for NvTensorRtRtx EP by @anujj in https://github.com/microsoft/onnxruntime-genai/pull/1697
- Use updated Decoder API with
skip_special_tokensby @sayanshaw24 in https://github.com/microsoft/onnxruntime-genai/pull/1722 - Update extensions to include memleak fix by @baijumeswani in https://github.com/microsoft/onnxruntime-genai/pull/1724
- Support batch processing for whisper example by @jiafatom in https://github.com/microsoft/onnxruntime-genai/pull/1723
- Update onnxruntime_extensions dependency version by @baijumeswani in https://github.com/microsoft/onnxruntime-genai/pull/1725
- Include C++ header in native nuget and fix compiler warnings by @baijumeswani in https://github.com/microsoft/onnxruntime-genai/pull/1727
- Update Microsoft.Extensions.AI to 9.8.0 by @rogerbarreto in https://github.com/microsoft/onnxruntime-genai/pull/1689
- Update Extensions commit for Qwen 2.5 Chat Template Tools Fix by @sayanshaw24 in https://github.com/microsoft/onnxruntime-genai/pull/1730
- Whisper Truncation Extensions Commit Update by @sayanshaw24 in https://github.com/microsoft/onnxruntime-genai/pull/1735
- Enable Cuda Graph for TensorRtRtx by default by @anujj in https://github.com/microsoft/onnxruntime-genai/pull/1734
- Update sampling benchmark by @tianleiwu in https://github.com/microsoft/onnxruntime-genai/pull/1729
- Add Windows WinML x64 build workflow by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1740
- Fix CUDA synchronization issue between ORT-GenAI and TRT-RTX inference by @anujj in https://github.com/microsoft/onnxruntime-genai/pull/1733
- Hello WindowsML by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1711
- [CUDA] sampling kernel improvements by @tianleiwu in https://github.com/microsoft/onnxruntime-genai/pull/1732
- Update GitHub Actions to latest versions by @snnn in https://github.com/microsoft/onnxruntime-genai/pull/1749
- Update WinML version to 1.8.2091 by @nieubank in https://github.com/microsoft/onnxruntime-genai/pull/1750
- Address macos packaging pipeline issues by @baijumeswani in https://github.com/microsoft/onnxruntime-genai/pull/1747
- ProviderOptions level device filtering and APIs to configure model level device filtering by @vortex-captain in https://github.com/microsoft/onnxruntime-genai/pull/1744
- Fix string indexing bug with Phi-4 mm tokenization by @kunal-vaishnavi in https://github.com/microsoft/onnxruntime-genai/pull/1751
- Fix TRT-RTX EP regression by @gaugarg-nv in https://github.com/microsoft/onnxruntime-genai/pull/1754
- Fix typo in C API header by @kunal-vaishnavi in https://github.com/microsoft/onnxruntime-genai/pull/1753
- Enable WinML by default in ADO pipelines by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1755
- Change default build configuration to 'relwithdebinfo' by @baijumeswani in https://github.com/microsoft/onnxruntime-genai/pull/1757
- Pin cmake and vcpkg versions in macOS workflows by @snnn in https://github.com/microsoft/onnxruntime-genai/pull/1760
- Add TRT_RTX support for onnxruntime-genai-trt-rtx wheel by @anujj in https://github.com/microsoft/onnxruntime-genai/pull/1736
- rel-0.10.0 by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1767
- Microsoft.ML.OnnxRuntimeGenAI.WinML.props by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1776
- Warning fix - ort_genai.h by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1778
- Microsoft.ML.OnnxRuntimeGenAI.targets by @chrisdMSFT in https://github.com/microsoft/onnxruntime-genai/pull/1781
New Contributors
- @nieubank made their first contribution in https://github.com/microsoft/onnxruntime-genai/pull/1750
Full Changelog: https://github.com/microsoft/onnxruntime-genai/compare/v0.9.2...v0.10.0