v1.17.1
版本发布时间: 2024-02-28 02:34:20
microsoft/onnxruntime最新发布版本:v1.19.2(2024-09-05 03:33:14)
This patch release includes the following updates:
General
- Update thread affinity on server so it is only set with auto affinity (#19318) - @ivberg
Build System and Packages
- Fix bug that was breaking arm64 build by disabling __cpuid check on arm64 builds since intrinsic is not available (#19574) - @smk2007
Core
- Add capturestate / rundown ETW support logging for session and provider options (#19397) - @ivberg
- Restrict L2 cache core check on Intel devices (#19483) - @smk2007
Performance
- Optimize KahnsTopologicalSort and PriorityNodeCompare to fix performance degradation in session creation time that was affecting many models (#19475) - @smk2007
EPs
- Enable DirectML on Windows and CUDA on Linux for Node.js binding (#19274) - @jchen351
QNN
- Fix split index bugs uncovered by QNN SDK 2.19 release (#19381) - @adrianlizarraga
- Add job that builds x64 Python wheels for QNN EP so cached QNN models can be created on Windows x64 (#19499) - @adrianlizarraga
OpenVINO
- Fix bugs for API backwards compatibility (#19482) - @preetha-intel
DirectML
- Fix bug in external data packing that was causing crash (#19415) - @PatriceVignola
- Fix bug in allocation planner by disabling streams for DML EP (#19481) - @PatriceVignola
Web
- Fix bug with types export in package.json (#19458) - @fs-eire
Training
- Reduce onnxruntime-training package size so it can be published on PyPI (#19486) - @baijumeswani
- Update default std flag used during torch extensions compilation (#19516) - @baijumeswani
- Add ATen fallback support for bicubic interpolation algorithm (#19380) - @prathikr
Quantization
- Update Q/DQ quantization to ensure Microsoft opset (#19335) - @adrianlizarraga
- Add contrib Q/DQ ops to symbolic shape inference tool (#19340) - @adrianlizarraga
- Fix subgraph quantization regression (#19421) - @fxmarty
- Add DefaultTensorType option to specify the default tensor type to quantize (#19455) - @yufenglee
- Fix bug with command line argparse to process --symmetric [True|False] correctly (#19577) - @satyajandhyala
Whisper Model
1、 Microsoft.AI.MachineLearning.1.17.1.nupkg 29.35MB
2、 Microsoft.AI.MachineLearning.1.17.1.snupkg 225.13MB
3、 Microsoft.ML.OnnxRuntime.DirectML.1.17.1.zip 13.69MB
4、 onnxruntime-linux-aarch64-1.17.1.tgz 4.69MB
5、 onnxruntime-linux-x64-1.17.1.tgz 5.52MB
6、 onnxruntime-linux-x64-cuda12-1.17.1.tgz 161.27MB
7、 onnxruntime-linux-x64-gpu-1.17.1.tgz 162.88MB
8、 onnxruntime-osx-arm64-1.17.1.tgz 6.91MB
9、 onnxruntime-osx-universal2-1.17.1.tgz 14.46MB
10、 onnxruntime-osx-x86_64-1.17.1.tgz 7.68MB
11、 onnxruntime-training-linux-aarch64-1.17.1.tgz 5.04MB
12、 onnxruntime-training-linux-x64-1.17.1.tgz 5.94MB
13、 onnxruntime-training-win-arm-1.17.1.zip 60.07MB
14、 onnxruntime-training-win-arm64-1.17.1.zip 62.51MB
15、 onnxruntime-training-win-x64-1.17.1.zip 63.25MB
16、 onnxruntime-training-win-x86-1.17.1.zip 61.73MB
17、 onnxruntime-win-arm64-1.17.1.zip 58.3MB
18、 onnxruntime-win-x64-1.17.1.zip 58.36MB
19、 onnxruntime-win-x64-cuda12-1.17.1.zip 186.11MB
20、 onnxruntime-win-x64-gpu-1.17.1.zip 191.58MB
21、 onnxruntime-win-x86-1.17.1.zip 57.45MB