You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by "dependabot[bot] (via GitHub)" <gi...@apache.org> on 2026/08/17 04:12:18 UTC
[PR] [2.x]: Bump onnxruntime.version from 1.28.0 to 1.29.0 (opennlp)
dependabot[bot] opened a new pull request, #1226:
URL: https://github.com/apache/opennlp/pull/1226
Bumps `onnxruntime.version` from 1.28.0 to 1.29.0.
Updates `com.microsoft.onnxruntime:onnxruntime` from 1.28.0 to 1.29.0
<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 v1.29.0</h2>
<h2>Announcements & Breaking Changes</h2>
<ul>
<li>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 (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29716">#29716</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31683">#31683</a>).</li>
<li>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 <code>ORT_DISABLE_TELEMETRY=1</code> before initialization disables non-Windows telemetry for the process (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/27379">#27379</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29872">#29872</a>).</li>
<li>The unused internal <code>onnxruntime/python/tools/tensorrt</code> dashboard tooling was removed. This does not affect the TensorRT Execution Provider APIs (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29395">#29395</a>).</li>
</ul>
<h2>Security Fixes</h2>
<h3>Path, bounds, and input validation</h3>
<ul>
<li>Fixed a path traversal vulnerability in TensorRT and NvTensorRTRTX engine refitting by making external-data path validation unconditional (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29396">#29396</a>).</li>
<li>Validated the CPU MoE <code>k</code> attribute against the number of experts and fixed a CPU <code>TensorScatter</code> security issue (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29907">#29907</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29916">#29916</a>).</li>
<li>Added missing rank, shape, and parameter validation for pooling, LSTM and DynamicQuantizeLSTM, Sampling, FeatureVectorizer, SkipLayerNorm, QLinearConv, Whisper decoding, RNN activations, GridSample, contrib <code>Range</code>, and <code>CropAndResize</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29254">#29254</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29255">#29255</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29265">#29265</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29579">#29579</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29595">#29595</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29605">#29605</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29871">#29871</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31636">#31636</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/3167
1">#31671</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31675">#31675</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31676">#31676</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31684">#31684</a>).</li>
<li>Hardened CUDA indexing and buffer handling in GridSample, transpose, GatherBlockQuantized, InstanceNormalization, LayerNorm/RMSNorm, BeamSearch, DeformConv, AveragePool, and MaxPool (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29581">#29581</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29631">#29631</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29638">#29638</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31640">#31640</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31642">#31642</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31644">#31644</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31645">#31645</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31647">#31647</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31650">#31650</a>).</li>
<li>Fixed packed sub-byte tensor over-copying in <code>OrtApi::GetValue</code> and validated DML constant tensor byte sizes (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29157">#29157</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31665">#31665</a>).</li>
</ul>
<h3>Supply chain and tooling</h3>
<ul>
<li>Updated npm lockfiles, refreshed the Next.js end-to-end fixture lockfile for security advisories, and upgraded <code>adm-zip</code> for <code>onnxruntime-node</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29827">#29827</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29926">#29926</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31192">#31192</a>).</li>
</ul>
<h2>New Features</h2>
<h3>Core APIs & Runtime</h3>
<ul>
<li>Default intra-op and inter-op thread-pool sizes can now be set with <code>ORT_INTRA_OP_NUM_THREADS</code> and <code>ORT_INTER_OP_NUM_THREADS</code>. Explicit thread settings still take precedence, and <code>0</code> preserves machine-sized defaults (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29688">#29688</a>).</li>
<li>Added weightless-model support for all initializer types, allowed zero-input <code>EpContext</code> nodes, and wired maximum-shape inference into workspace estimation (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29607">#29607</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29799">#29799</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31613">#31613</a>).</li>
<li>Added ONNX-domain support for rotary embedding and a fused <code>MRotaryEmbedding</code> contrib operator for Qwen mRoPE variants (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29261">#29261</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31728">#31728</a>).</li>
<li>Added multi-shape profiling to <code>onnxruntime_perf_test</code> through <code>--data_shape</code>, plus verbose graph-transformer tracing and broader inference-session error-path coverage (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29555">#29555</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29558">#29558</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29569">#29569</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29571">#29571</a>).</li>
</ul>
<h3>Execution Provider ABI & Plugin EPs</h3>
<ul>
<li>WebGPU now supports device-free compile-only sessions for offline graph transformation (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29681">#29681</a>).</li>
<li>Expanded CUDA plugin EP packaging and testing, including Windows ARM64 package and size options, updated package outputs, and aligned architecture selections across Python, C API, TensorRT, Node.js, and plugin packages (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/31635">#31635</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31722">#31722</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31992">#31992</a>).</li>
<li>Improved plugin lifecycle handling by unloading failed EP library loads and fixing allocator-deleter lifetime (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29634">#29634</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29770">#29770</a>).</li>
</ul>
<h2>Execution Provider Updates</h2>
<h3>NVIDIA CUDA EP</h3>
<h4>Attention and decoding</h4>
<ul>
<li>Added <code>PagedAttention</code> with quantized KV cache, XQA decode, MLA, QK-Norm, and head-sink support (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29912">#29912</a>).</li>
<li>Extended quantized KV-cache support with attention sinks, independent and per-channel scales, sliding-window cache support, and a fused K/V dequantization launch (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29900">#29900</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29904">#29904</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31480">#31480</a>).</li>
<li>Added a cuDNN SDPA decode tier to the standard ONNX <code>Attention</code> CUDA kernel and enabled cuDNN SDPA for contrib <code>Attention</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29715">#29715</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29717">#29717</a>).</li>
<li>Added <code>attention_bias</code> support to the GroupQueryAttention unfused path and <code>state_window</code> support to LinearAttention and CausalConvWithState for MTP (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29525">#29525</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31157">#31157</a>).</li>
<li>Fixed LinearAttention on GPUs with limited shared memory (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/31982">#31982</a>).</li>
</ul>
<h4>MoE and quantized GEMM</h4>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a href="https://github.com/microsoft/onnxruntime/commit/2e2543fbe9fae542f921d47a72d21d5a4ef0b710"><code>2e2543f</code></a> [CUDA] Update cuda archs in packaging pipelines (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31992">#31992</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/9b174a42fcf8fb41d6f5f99f7102b8f650b5558f"><code>9b174a4</code></a> [CUDA] Add GatedAdd contrib operator (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31835">#31835</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/a29da16687ecb3ab665a1dbdadf3f958559f376b"><code>a29da16</code></a> Validate SkipLayerNorm prepacked lengths (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31676">#31676</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/831fa2fe2b89cfd59506927e6125015e8fca1ab6"><code>831fa2f</code></a> Validate whisper beginning_timestamp_token_id bounds (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31636">#31636</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/3cee186058ef3712d420bbd3c2f2e4cc2feea773"><code>3cee186</code></a> Handle RNN activation parameters safely (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31675">#31675</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/37d79e38a5f513427a961c328b117f6fd2959e43"><code>37d79e3</code></a> Harden CUDA fp16 transpose index math against int overflow (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31644">#31644</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/45bdd4c47284b619549fbba6bc2012b6ed7f218a"><code>45bdd4c</code></a> Validate QLinearConv bias size against output channels (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31684">#31684</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/f5de4c394598e91846d01bed500d1253efeee73b"><code>f5de4c3</code></a> Fix TfIdfVectorizer weight indexing semantics (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31649">#31649</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/d3abafc3d78d6f4a0842b25de3a2d62eea6445cc"><code>d3abafc</code></a> Validate FeatureVectorizer batch sizes (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31671">#31671</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/1441b36d045d8ceb0d6b52793c181b2c86d8cfa7"><code>1441b36</code></a> [WebGPU] Add MRotaryEmbedding support (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31976">#31976</a>)</li>
<li>Additional commits viewable in <a href="https://github.com/microsoft/onnxruntime/compare/v1.28.0...v1.29.0">compare view</a></li>
</ul>
</details>
<br />
Updates `com.microsoft.onnxruntime:onnxruntime_gpu` from 1.28.0 to 1.29.0
<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 v1.29.0</h2>
<h2>Announcements & Breaking Changes</h2>
<ul>
<li>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 (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29716">#29716</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31683">#31683</a>).</li>
<li>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 <code>ORT_DISABLE_TELEMETRY=1</code> before initialization disables non-Windows telemetry for the process (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/27379">#27379</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29872">#29872</a>).</li>
<li>The unused internal <code>onnxruntime/python/tools/tensorrt</code> dashboard tooling was removed. This does not affect the TensorRT Execution Provider APIs (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29395">#29395</a>).</li>
</ul>
<h2>Security Fixes</h2>
<h3>Path, bounds, and input validation</h3>
<ul>
<li>Fixed a path traversal vulnerability in TensorRT and NvTensorRTRTX engine refitting by making external-data path validation unconditional (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29396">#29396</a>).</li>
<li>Validated the CPU MoE <code>k</code> attribute against the number of experts and fixed a CPU <code>TensorScatter</code> security issue (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29907">#29907</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29916">#29916</a>).</li>
<li>Added missing rank, shape, and parameter validation for pooling, LSTM and DynamicQuantizeLSTM, Sampling, FeatureVectorizer, SkipLayerNorm, QLinearConv, Whisper decoding, RNN activations, GridSample, contrib <code>Range</code>, and <code>CropAndResize</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29254">#29254</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29255">#29255</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29265">#29265</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29579">#29579</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29595">#29595</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29605">#29605</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29871">#29871</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31636">#31636</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/3167
1">#31671</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31675">#31675</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31676">#31676</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31684">#31684</a>).</li>
<li>Hardened CUDA indexing and buffer handling in GridSample, transpose, GatherBlockQuantized, InstanceNormalization, LayerNorm/RMSNorm, BeamSearch, DeformConv, AveragePool, and MaxPool (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29581">#29581</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29631">#29631</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29638">#29638</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31640">#31640</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31642">#31642</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31644">#31644</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31645">#31645</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31647">#31647</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31650">#31650</a>).</li>
<li>Fixed packed sub-byte tensor over-copying in <code>OrtApi::GetValue</code> and validated DML constant tensor byte sizes (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29157">#29157</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31665">#31665</a>).</li>
</ul>
<h3>Supply chain and tooling</h3>
<ul>
<li>Updated npm lockfiles, refreshed the Next.js end-to-end fixture lockfile for security advisories, and upgraded <code>adm-zip</code> for <code>onnxruntime-node</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29827">#29827</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29926">#29926</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31192">#31192</a>).</li>
</ul>
<h2>New Features</h2>
<h3>Core APIs & Runtime</h3>
<ul>
<li>Default intra-op and inter-op thread-pool sizes can now be set with <code>ORT_INTRA_OP_NUM_THREADS</code> and <code>ORT_INTER_OP_NUM_THREADS</code>. Explicit thread settings still take precedence, and <code>0</code> preserves machine-sized defaults (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29688">#29688</a>).</li>
<li>Added weightless-model support for all initializer types, allowed zero-input <code>EpContext</code> nodes, and wired maximum-shape inference into workspace estimation (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29607">#29607</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29799">#29799</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31613">#31613</a>).</li>
<li>Added ONNX-domain support for rotary embedding and a fused <code>MRotaryEmbedding</code> contrib operator for Qwen mRoPE variants (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29261">#29261</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31728">#31728</a>).</li>
<li>Added multi-shape profiling to <code>onnxruntime_perf_test</code> through <code>--data_shape</code>, plus verbose graph-transformer tracing and broader inference-session error-path coverage (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29555">#29555</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29558">#29558</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29569">#29569</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29571">#29571</a>).</li>
</ul>
<h3>Execution Provider ABI & Plugin EPs</h3>
<ul>
<li>WebGPU now supports device-free compile-only sessions for offline graph transformation (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29681">#29681</a>).</li>
<li>Expanded CUDA plugin EP packaging and testing, including Windows ARM64 package and size options, updated package outputs, and aligned architecture selections across Python, C API, TensorRT, Node.js, and plugin packages (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/31635">#31635</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31722">#31722</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31992">#31992</a>).</li>
<li>Improved plugin lifecycle handling by unloading failed EP library loads and fixing allocator-deleter lifetime (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29634">#29634</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29770">#29770</a>).</li>
</ul>
<h2>Execution Provider Updates</h2>
<h3>NVIDIA CUDA EP</h3>
<h4>Attention and decoding</h4>
<ul>
<li>Added <code>PagedAttention</code> with quantized KV cache, XQA decode, MLA, QK-Norm, and head-sink support (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29912">#29912</a>).</li>
<li>Extended quantized KV-cache support with attention sinks, independent and per-channel scales, sliding-window cache support, and a fused K/V dequantization launch (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29900">#29900</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29904">#29904</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31480">#31480</a>).</li>
<li>Added a cuDNN SDPA decode tier to the standard ONNX <code>Attention</code> CUDA kernel and enabled cuDNN SDPA for contrib <code>Attention</code> (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29715">#29715</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/29717">#29717</a>).</li>
<li>Added <code>attention_bias</code> support to the GroupQueryAttention unfused path and <code>state_window</code> support to LinearAttention and CausalConvWithState for MTP (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/29525">#29525</a>, <a href="https://redirect.github.com/microsoft/onnxruntime/pull/31157">#31157</a>).</li>
<li>Fixed LinearAttention on GPUs with limited shared memory (<a href="https://redirect.github.com/microsoft/onnxruntime/pull/31982">#31982</a>).</li>
</ul>
<h4>MoE and quantized GEMM</h4>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a href="https://github.com/microsoft/onnxruntime/commit/2e2543fbe9fae542f921d47a72d21d5a4ef0b710"><code>2e2543f</code></a> [CUDA] Update cuda archs in packaging pipelines (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31992">#31992</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/9b174a42fcf8fb41d6f5f99f7102b8f650b5558f"><code>9b174a4</code></a> [CUDA] Add GatedAdd contrib operator (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31835">#31835</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/a29da16687ecb3ab665a1dbdadf3f958559f376b"><code>a29da16</code></a> Validate SkipLayerNorm prepacked lengths (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31676">#31676</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/831fa2fe2b89cfd59506927e6125015e8fca1ab6"><code>831fa2f</code></a> Validate whisper beginning_timestamp_token_id bounds (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31636">#31636</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/3cee186058ef3712d420bbd3c2f2e4cc2feea773"><code>3cee186</code></a> Handle RNN activation parameters safely (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31675">#31675</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/37d79e38a5f513427a961c328b117f6fd2959e43"><code>37d79e3</code></a> Harden CUDA fp16 transpose index math against int overflow (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31644">#31644</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/45bdd4c47284b619549fbba6bc2012b6ed7f218a"><code>45bdd4c</code></a> Validate QLinearConv bias size against output channels (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31684">#31684</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/f5de4c394598e91846d01bed500d1253efeee73b"><code>f5de4c3</code></a> Fix TfIdfVectorizer weight indexing semantics (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31649">#31649</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/d3abafc3d78d6f4a0842b25de3a2d62eea6445cc"><code>d3abafc</code></a> Validate FeatureVectorizer batch sizes (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31671">#31671</a>)</li>
<li><a href="https://github.com/microsoft/onnxruntime/commit/1441b36d045d8ceb0d6b52793c181b2c86d8cfa7"><code>1441b36</code></a> [WebGPU] Add MRotaryEmbedding support (<a href="https://redirect.github.com/microsoft/onnxruntime/issues/31976">#31976</a>)</li>
<li>Additional commits viewable in <a href="https://github.com/microsoft/onnxruntime/compare/v1.28.0...v1.29.0">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 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: commits-unsubscribe@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [2.x]: Bump onnxruntime.version from 1.28.0 to 1.29.0 (opennlp)
Posted by "jzonthemtn (via GitHub)" <gi...@apache.org>.
jzonthemtn merged PR #1226:
URL: https://github.com/apache/opennlp/pull/1226
--
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: commits-unsubscribe@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org