dependabot[bot] opened a new pull request, #680: URL: https://github.com/apache/opennlp/pull/680
Bumps `onnxruntime.version` from 1.19.2 to 1.20.0. Updates `com.microsoft.onnxruntime:onnxruntime` from 1.19.2 to 1.20.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/microsoft/onnxruntime/releases";>com.microsoft.onnxruntime:onnxruntime's releases</a>.</em></p> <blockquote> <h2>ONNX Runtime v1.20.0</h2> <p><strong>Release Manager: <a href="https://github.com/apsonawane";><code>@apsonawane</code></a></strong></p> <h1>Announcements</h1> <ul> <li><strong>All ONNX Runtime Training packages have been deprecated.</strong> ORT 1.19.2 was the last release for which onnxruntime-training (PyPI), onnxruntime-training-cpu (PyPI), Microsoft.ML.OnnxRuntime.Training (Nuget), onnxruntime-training-c (CocoaPods), onnxruntime-training-objc (CocoaPods), and onnxruntime-training-android (Maven Central) were published.</li> <li><strong>ONNX Runtime packages will stop supporting Python 3.8 and Python 3.9.</strong> This decision aligns with NumPy Python version support. To continue using ORT with Python 3.8 and Python 3.9, you can use ORT 1.19.2 and earlier.</li> <li><strong>ONNX Runtime 1.20 CUDA packages will include new dependencies that were not required in 1.19 packages.</strong> The following dependencies are new: libcudnn_adv.so.9, libcudnn_cnn.so.9, libcudnn_engines_precompiled.so.9, libcudnn_engines_runtime_compiled.so.9, libcudnn_graph.so.9, libcudnn_heuristic.so.9, libcudnn_ops.so.9, libnvrtc.so.12, and libz.so.1.</li> </ul> <h1>Build System & Packages</h1> <ul> <li>Python 3.13 support is included in PyPI packages.</li> <li>ONNX 1.17 support will be delayed until a future release, but the ONNX version used by ONNX Runtime has been patched to include a <a href="https://redirect.github.com/onnx/onnx/pull/6010";>shape inference change to the Einsum op</a>.</li> <li>DLLs in the Maven build are now digitally signed (fix for issue reported <a href="https://redirect.github.com/microsoft/onnxruntime/issues/19204";>here</a>).</li> <li>(Experimental) vcpkg support added for the CPU EP. The DML EP does not yet support vcpkg, and other EPs have not been tested.</li> </ul> <h1>Core</h1> <ul> <li>MultiLoRA support.</li> <li>Reduced memory utilization. <ul> <li>Fixed alignment that was causing mmap to fail for external weights.</li> <li>Eliminated double allocations when deserializing external weights.</li> <li>Added ability to serialize pre-packed weights so that they don’t cause an increase in memory utilization when the model is loaded.</li> </ul> </li> <li>Support bfloat16 and float8 data types in python I/O binding API.</li> </ul> <h1>Performance</h1> <ul> <li>INT4 quantized embedding support on CPU and CUDA EPs.</li> <li>Miscellaneous performance improvements and bug fixes.</li> </ul> <h1>EPs</h1> <h2>CPU</h2> <ul> <li>FP16 support for MatMulNbits, Clip, and LayerNormalization ops.</li> </ul> <h2>CUDA</h2> <ul> <li>Added support of cuDNN Flash Attention and Lean Attention in MultiHeadAttention op.</li> </ul> <h2>TensorRT</h2> <ul> <li>TensorRT <a href="https://github.com/NVIDIA/TensorRT/releases/tag/v10.4.0";>10.4</a> and <a href="https://github.com/NVIDIA/TensorRT/releases/tag/v10.5.0";>10.5</a> support.</li> </ul> <h2>QNN</h2> <ul> <li>QNN HTP support for weight sharing across multiple ORT inference sessions. (See <a href="https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html#qnn-ep-weight-sharing";>ORT QNN EP documentation</a> for more information.)</li> <li>Support for QNN SDK 2.27.</li> </ul> <h2>OpenVINO</h2> <ul> <li>Added support up to OpenVINO 2024.4.1.</li> <li>Compile-time memory optimizations.</li> <li>Enhancement of ORT EPContext Session option for optimized first inference latency.</li> <li>Added remote tensors to ensure direct memory access for inferencing on NPU.</li> </ul> <h2>DirectML</h2> <ul> <li><a href="https://www.nuget.org/packages/Microsoft.AI.DirectML/1.15.2";>DirectML 1.15.2</a> support.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/microsoft/onnxruntime/commit/c4fb724e810bb496165b9015c77f402727392933";><code>c4fb724</code></a> ORT 1.20.0 release preparation: Cherry pick round 2 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22643";>#22643</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/2d00351d7b4975a4d03f6a437772b6976726a252";><code>2d00351</code></a> ORT 1.20.0 Release: Cherry pick round 1 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22526";>#22526</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/f9e623e4d1cf0998e5499053d96ab5f77ddff6d0";><code>f9e623e</code></a> Update CMake to 3.31.0rc1 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22433";>#22433</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/691de83892e72f38bffd39c47777980a6c362b97";><code>691de83</code></a> Enable BrowserStack tests (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22457";>#22457</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/bf604428aa4b9faf84ce99f735ad6402a6d6f886";><code>bf60442</code></a> [ROCm] Update ROCm Nuget pipeline to ROCm 6.2 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22461";>#22461</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/2b8fc5529bce4d815d2e71e9c8258c29db377c87";><code>2b8fc55</code></a> Enable RunMatMulTest all test cases support FP16 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22440";>#22440</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/af00a20f8aeba17a68ea8a7c5f41df2c27d96116";><code>af00a20</code></a> Change ORT nightly python packages' name (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22450";>#22450</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/a5e85a950c2fab5729c46e7362a60765caa4b999";><code>a5e85a9</code></a> Fix training artifacts for 2GB+ models and <code>MSELoss</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22414";>#22414</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/6407d81b35436cfa0d74dd39f05a182d750b572e";><code>6407d81</code></a> Disable BrowserStack testing stage (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22438";>#22438</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/4c47bca8fefa654a6c7b043293bb92161492f6e6";><code>4c47bca</code></a> [MIGraphX EP] Add additional operators (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22446";>#22446</a>)</li> <li>Additional commits viewable in <a href="https://github.com/microsoft/onnxruntime/compare/v1.19.2...v1.20.0";>compare view</a></li> </ul> </details> <br /> Updates `com.microsoft.onnxruntime:onnxruntime_gpu` from 1.19.2 to 1.20.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/microsoft/onnxruntime/releases";>com.microsoft.onnxruntime:onnxruntime_gpu's releases</a>.</em></p> <blockquote> <h2>ONNX Runtime v1.20.0</h2> <p><strong>Release Manager: <a href="https://github.com/apsonawane";><code>@apsonawane</code></a></strong></p> <h1>Announcements</h1> <ul> <li><strong>All ONNX Runtime Training packages have been deprecated.</strong> ORT 1.19.2 was the last release for which onnxruntime-training (PyPI), onnxruntime-training-cpu (PyPI), Microsoft.ML.OnnxRuntime.Training (Nuget), onnxruntime-training-c (CocoaPods), onnxruntime-training-objc (CocoaPods), and onnxruntime-training-android (Maven Central) were published.</li> <li><strong>ONNX Runtime packages will stop supporting Python 3.8 and Python 3.9.</strong> This decision aligns with NumPy Python version support. To continue using ORT with Python 3.8 and Python 3.9, you can use ORT 1.19.2 and earlier.</li> <li><strong>ONNX Runtime 1.20 CUDA packages will include new dependencies that were not required in 1.19 packages.</strong> The following dependencies are new: libcudnn_adv.so.9, libcudnn_cnn.so.9, libcudnn_engines_precompiled.so.9, libcudnn_engines_runtime_compiled.so.9, libcudnn_graph.so.9, libcudnn_heuristic.so.9, libcudnn_ops.so.9, libnvrtc.so.12, and libz.so.1.</li> </ul> <h1>Build System & Packages</h1> <ul> <li>Python 3.13 support is included in PyPI packages.</li> <li>ONNX 1.17 support will be delayed until a future release, but the ONNX version used by ONNX Runtime has been patched to include a <a href="https://redirect.github.com/onnx/onnx/pull/6010";>shape inference change to the Einsum op</a>.</li> <li>DLLs in the Maven build are now digitally signed (fix for issue reported <a href="https://redirect.github.com/microsoft/onnxruntime/issues/19204";>here</a>).</li> <li>(Experimental) vcpkg support added for the CPU EP. The DML EP does not yet support vcpkg, and other EPs have not been tested.</li> </ul> <h1>Core</h1> <ul> <li>MultiLoRA support.</li> <li>Reduced memory utilization. <ul> <li>Fixed alignment that was causing mmap to fail for external weights.</li> <li>Eliminated double allocations when deserializing external weights.</li> <li>Added ability to serialize pre-packed weights so that they don’t cause an increase in memory utilization when the model is loaded.</li> </ul> </li> <li>Support bfloat16 and float8 data types in python I/O binding API.</li> </ul> <h1>Performance</h1> <ul> <li>INT4 quantized embedding support on CPU and CUDA EPs.</li> <li>Miscellaneous performance improvements and bug fixes.</li> </ul> <h1>EPs</h1> <h2>CPU</h2> <ul> <li>FP16 support for MatMulNbits, Clip, and LayerNormalization ops.</li> </ul> <h2>CUDA</h2> <ul> <li>Added support of cuDNN Flash Attention and Lean Attention in MultiHeadAttention op.</li> </ul> <h2>TensorRT</h2> <ul> <li>TensorRT <a href="https://github.com/NVIDIA/TensorRT/releases/tag/v10.4.0";>10.4</a> and <a href="https://github.com/NVIDIA/TensorRT/releases/tag/v10.5.0";>10.5</a> support.</li> </ul> <h2>QNN</h2> <ul> <li>QNN HTP support for weight sharing across multiple ORT inference sessions. (See <a href="https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html#qnn-ep-weight-sharing";>ORT QNN EP documentation</a> for more information.)</li> <li>Support for QNN SDK 2.27.</li> </ul> <h2>OpenVINO</h2> <ul> <li>Added support up to OpenVINO 2024.4.1.</li> <li>Compile-time memory optimizations.</li> <li>Enhancement of ORT EPContext Session option for optimized first inference latency.</li> <li>Added remote tensors to ensure direct memory access for inferencing on NPU.</li> </ul> <h2>DirectML</h2> <ul> <li><a href="https://www.nuget.org/packages/Microsoft.AI.DirectML/1.15.2";>DirectML 1.15.2</a> support.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/microsoft/onnxruntime/commit/c4fb724e810bb496165b9015c77f402727392933";><code>c4fb724</code></a> ORT 1.20.0 release preparation: Cherry pick round 2 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22643";>#22643</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/2d00351d7b4975a4d03f6a437772b6976726a252";><code>2d00351</code></a> ORT 1.20.0 Release: Cherry pick round 1 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22526";>#22526</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/f9e623e4d1cf0998e5499053d96ab5f77ddff6d0";><code>f9e623e</code></a> Update CMake to 3.31.0rc1 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22433";>#22433</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/691de83892e72f38bffd39c47777980a6c362b97";><code>691de83</code></a> Enable BrowserStack tests (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22457";>#22457</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/bf604428aa4b9faf84ce99f735ad6402a6d6f886";><code>bf60442</code></a> [ROCm] Update ROCm Nuget pipeline to ROCm 6.2 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22461";>#22461</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/2b8fc5529bce4d815d2e71e9c8258c29db377c87";><code>2b8fc55</code></a> Enable RunMatMulTest all test cases support FP16 (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22440";>#22440</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/af00a20f8aeba17a68ea8a7c5f41df2c27d96116";><code>af00a20</code></a> Change ORT nightly python packages' name (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22450";>#22450</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/a5e85a950c2fab5729c46e7362a60765caa4b999";><code>a5e85a9</code></a> Fix training artifacts for 2GB+ models and <code>MSELoss</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22414";>#22414</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/6407d81b35436cfa0d74dd39f05a182d750b572e";><code>6407d81</code></a> Disable BrowserStack testing stage (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22438";>#22438</a>)</li> <li><a href="https://github.com/microsoft/onnxruntime/commit/4c47bca8fefa654a6c7b043293bb92161492f6e6";><code>4c47bca</code></a> [MIGraphX EP] Add additional operators (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/22446";>#22446</a>)</li> <li>Additional commits viewable in <a href="https://github.com/microsoft/onnxruntime/compare/v1.19.2...v1.20.0";>compare view</a></li> </ul> </details> <br /> Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@opennlp.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
