ONNX Runtime 发布: ONNX Runtime v1.29.0

来源摘要

## Announcements & Breaking Changes - onnxruntime-web has announced the deprecation of WebGL and JSEP. The native WebGPU EP is the recommended path going forward. See the deprecation and migration plans for details ([#29716](https://github.com/microsoft/onnxruntime/pull/29716), [#31683](https://github.com/microsoft/onnxruntime/pull/31683)). - POSIX telemetry is now available on Linux, macOS, Android, and iOS when ONNX Runtime is built with telemetry enabled. It does not change the public ABI, WebAssembly remains telemetry-free, and setting `ORT_DISABLE_TELEMETRY=1` before initialization disables non-Windows telemetry for the process ([#27379](https://github.com/microsoft/onnxruntime/pull/27379), [#29872](https://github.com/microsoft/onnxruntime/pull/29872)). - The unused internal `onnxruntime/python/tools/tensorrt` dashboard tooling was removed. This does not affect the TensorRT Execution Provider APIs ([#29395](https://github.com/microsoft/onnxruntime/pull/29395)). ## Security Fixes ### Path, bounds, and input validation - Fixed a path traversal vulnerability in TensorRT and NvTensorRTRTX engine refitting by making external-data path validation unconditional ([#29396](https://github.com/microsoft/onnxruntime/pull/29396)). - Validated the CPU MoE `k` attribute against the number of experts and fixed a CPU `TensorScatter` security issue ([#29907](https://github.com/microsoft/onnxruntime/pull/29907), [#29916](https://github.com/microsoft/onnxruntime/pull/29916)). - Added missing rank, shape, and parameter validation for pooling, LSTM and DynamicQuantizeLSTM, Sampling, FeatureVectorizer, SkipLayerNorm, QLinearConv, Whisper decoding, RNN activations, GridSample, contrib `Range`, and `CropAndResize` ([#29254](https://github.com/microsoft/onnxruntime/pull/29254), [#29255](htt