[webgpu] refactor a few "context" classes by fs-eire · Pull Request #26602 · microsoft/onnxruntime

fs-eire · 2025-11-19T02:40:26Z

Description

This PR refactors a few "context" classes to make it clearer and support new features.

…-context

Copilot

Pull request overview

This PR refactors WebGPU provider "context" classes to improve clarity, simplify initialization, and support new features like weight pre-packing. The main changes include:

Extracts ComputeContextBase as a base class that doesn't depend on OpKernelContext, enabling its use in pre-pack operations
Converts SplitKConfig from lazy initialization via static factory method to eager initialization via constructor
Adds PrePack and PrePackInternal infrastructure to WebGpuKernel for future weight optimization
Introduces WebGpuDevice constant to eliminate code duplication

Reviewed changes

Copilot reviewed 15 out of 15 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
webgpu_utils.h	Changes `SplitKConfig::GetSplitKConfig()` static method to constructor, adds documentation
webgpu_utils.cc	Implements constructor-based initialization for `SplitKConfig`
webgpu_context.h	Changes `split_k_config_` from `std::optional` to `std::unique_ptr`, updates method signatures to use `ComputeContextBase`, removes lazy initialization method
webgpu_context.cc	Adds eager initialization of `SplitKConfig` in `Initialize()`, removes old lazy initialization method, updates method signatures
webgpu_kernel.h	Adds `PrePack` and `PrePackInternal` methods, adds `webgpu_context_` member
webgpu_kernel.cc	Implements `PrePack` and default `PrePackInternal`, caches `webgpu_context_` reference, updates `ComputeContext` construction
compute_context.h	Extracts `ComputeContextBase` base class without `OpKernelContext` dependency, `ComputeContext` inherits from it
compute_context.cc	Updates constructors for base/derived class pattern
transpose.h/cc	Updates `DoTranspose` signature to accept `ComputeContextBase&`
conv.h	Adds `PrePackInternal` override and `transposed_kernel_` member for future implementation
conv.cc	Implements placeholder `PrePackInternal` with TODO for weight transpose optimization
webgpu_execution_provider.cc	Uses `WebGpuDevice` constant instead of inline construction
allocator.h	Defines `WebGpuDevice` constant
allocator.cc	Uses `WebGpuDevice` constant

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

onnxruntime/core/providers/webgpu/webgpu_kernel.h

onnxruntime/core/providers/webgpu/nn/conv.h

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Copilot · 2025-11-25T00:34:44Z

@fs-eire I've opened a new pull request, #26650, to work on those changes. Once the pull request is ready, I'll request review from you.

Copilot · 2025-11-25T00:35:02Z

@fs-eire I've opened a new pull request, #26651, to work on those changes. Once the pull request is ready, I'll request review from you.

…rnel (#26650) ### Description Adds documentation for `PrePack` and `PrePackInternal` methods in `webgpu_kernel.h`: - **`PrePack`**: Documents the WebGPU-specific override behavior, including the limitation that ORT does not pass prepacked weights to non-CPU EPs (kernels must manage their own storage) - **`PrePackInternal`**: Documents the virtual method's purpose, invocation timing, parameter semantics, and default `is_packed = false` behavior ### Motivation and Context Addresses review feedback from #26602 requesting documentation for these methods: - #26602 (comment) - #26602 (comment)  --- ✨ Let Copilot coding agent [set things up for you](https://github.com/microsoft/onnxruntime/issues/new?title=✨+Set+up+Copilot+instructions&body=Configure%20instructions%20for%20this%20repository%20as%20documented%20in%20%5BBest%20practices%20for%20Copilot%20coding%20agent%20in%20your%20repository%5D%28https://gh.io/copilot-coding-agent-tips%29%2E%0A%0A%3COnboard%20this%20repo%3E&assignees=copilot) — coding agent works faster and does higher quality work when set up for your repo. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: fs-eire <7679871+fs-eire@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 15 out of 15 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

onnxruntime/core/providers/webgpu/compute_context.cc

onnxruntime/core/providers/webgpu/nn/conv.cc

@guschmue

* Fix npm audit vulnerabilities in /js directory (microsoft#26632) ### Description Resolved all security vulnerabilities in JavaScript packages under `/js` by running `npm audit fix`. All updates are non-breaking patch/minor version bumps. **Fixed vulnerabilities:** - `/js` root: 1 high severity - `glob` 10.4.5 → 10.5.0 (command injection - GHSA-5j98-mcp5-4vw2) - `/js/react_native`: 7 vulnerabilities (1 high, 3 moderate, 3 low) - `image-size` → 1.2.1 (high: DoS via infinite loop - GHSA-m5qc-5hw7-8vg7) - `@babel/helpers` 7.25.6 → 7.28.4 (moderate: RegExp complexity - GHSA-968p-4wvh-cqc8) - `@babel/runtime` 7.25.6 → 7.28.4 (moderate: RegExp complexity - GHSA-968p-4wvh-cqc8) - `js-yaml` → fixed (moderate: prototype pollution - GHSA-mh29-5h37-fv8m) - `brace-expansion` 2.0.1 → 2.0.2 (low: ReDoS - GHSA-v6h2-p8h4-qcjw) - `on-headers` → fixed (low: header manipulation - GHSA-76c9-3jph-rj3q) **Files modified:** - `js/package-lock.json` - `js/react_native/package-lock.json` **Result:** All JS packages (`/js`, `/js/common`, `/js/web`, `/js/node`, `/js/react_native`) now report 0 vulnerabilities. ### Motivation and Context Security maintenance to address dependency vulnerabilities identified by `npm audit`. No breaking changes or code modifications required.  <details> <summary>Original prompt</summary> > Please create a pull request that runs `npm audit fix` for the JavaScript/TypeScript portion of the repository under the `/js` directory of [microsoft/onnxruntime](https://github.com/microsoft/onnxruntime). > > Requirements: > > 1. **Scope** > - Work only within the `/js` folder and its subpackages (e.g., `js/web`, `js/node`, `js/common`, etc.). > - Do not modify files outside `/js`. > > 2. **Dependency updates** > - Run `npm audit fix` (and, if necessary to fully resolve high/critical issues while staying non-breaking, `npm audit fix --force` on specific subpackages) to address security vulnerabilities. > - Prefer minimal, non-breaking version bumps (patch and minor) that satisfy `npm audit` while keeping semver ranges sensible. > - If any **major** upgrades are required to clear vulnerabilities, handle them cautiously: > - Apply the upgrade only if tests still pass and typings/build setup remain compatible. > - If a major bump would require code changes or creates breaking behavior, **do not** apply it; instead, leave a TODO comment in the PR description summarizing which packages remain vulnerable and why. > > 3. **Validation** > - Run the existing JS-related checks that the repo supports from `/js`, such as: > - `npm test` or package-specific test scripts. > - Any documented lint/build/test commands for JS packages (e.g., `npm run build`, `npm run lint`) where applicable. > - Ensure the updated lockfiles (if present) are consistent, and the project installs cleanly with `npm ci` (or the repo's documented install command) in the `/js` area. > > 4. **Files to update** > - Update `package.json` and lockfiles under `/js` (e.g., `package-lock.json`, `npm-shrinkwrap.json`, or workspace-specific lock files) to reflect the audited dependency tree. > - Do not manually edit `node_modules`; rely on `npm` to manage dependencies and only commit manifest/lockfile changes. > > 5. **Repository conventions** > - Follow this repo's existing conventions for formatting, commit messages, and JS tooling. > - Keep the diff focused on the dependency and lockfile updates plus any absolutely necessary code tweaks to maintain compatibility. > > 6. **Pull request description** > - In the PR body, include: > - A short summary: that `npm audit fix` was run in `/js` to address dependency vulnerabilities. > - A bullet list of notable dependency changes (especially any major version bumps), with packages and old/new versions. > - A brief testing summary (commands run and their results). > - A note about any remaining vulnerabilities that could not be fixed without breaking changes (if applicable), including the affected packages and advisories if available. > > The goal is a clean, minimal PR that improves the security posture of the JS packages under `/js` in `microsoft/onnxruntime` without introducing breaking changes. </details> *This pull request was created as a result of the following prompt from Copilot chat.* > Please create a pull request that runs `npm audit fix` for the JavaScript/TypeScript portion of the repository under the `/js` directory of [microsoft/onnxruntime](https://github.com/microsoft/onnxruntime). > > Requirements: > > 1. **Scope** > - Work only within the `/js` folder and its subpackages (e.g., `js/web`, `js/node`, `js/common`, etc.). > - Do not modify files outside `/js`. > > 2. **Dependency updates** > - Run `npm audit fix` (and, if necessary to fully resolve high/critical issues while staying non-breaking, `npm audit fix --force` on specific subpackages) to address security vulnerabilities. > - Prefer minimal, non-breaking version bumps (patch and minor) that satisfy `npm audit` while keeping semver ranges sensible. > - If any **major** upgrades are required to clear vulnerabilities, handle them cautiously: > - Apply the upgrade only if tests still pass and typings/build setup remain compatible. > - If a major bump would require code changes or creates breaking behavior, **do not** apply it; instead, leave a TODO comment in the PR description summarizing which packages remain vulnerable and why. > > 3. **Validation** > - Run the existing JS-related checks that the repo supports from `/js`, such as: > - `npm test` or package-specific test scripts. > - Any documented lint/build/test commands for JS packages (e.g., `npm run build`, `npm run lint`) where applicable. > - Ensure the updated lockfiles (if present) are consistent, and the project installs cleanly with `npm ci` (or the repo's documented install command) in the `/js` area. > > 4. **Files to update** > - Update `package.json` and lockfiles under `/js` (e.g., `package-lock.json`, `npm-shrinkwrap.json`, or workspace-specific lock files) to reflect the audited dependency tree. > - Do not manually edit `node_modules`; rely on `npm` to manage dependencies and only commit manifest/lockfile changes. > > 5. **Repository conventions** > - Follow this repo's existing conventions for formatting, commit messages, and JS tooling. > - Keep the diff focused on the dependency and lockfile updates plus any absolutely necessary code tweaks to maintain compatibility. > > 6. **Pull request description** > - In the PR body, include: > - A short summary: that `npm audit fix` was run in `/js` to address dependency vulnerabilities. > - A bullet list of notable dependency changes (especially any major version bumps), with packages and old/new versions. > - A brief testing summary (commands run and their results). > - A note about any remaining vulnerabilities that could not be fixed without breaking changes (if applicable), including the affected packages and advisories if available. > > The goal is a clean, minimal PR that improves the security posture of the JS packages under `/js` in `microsoft/onnxruntime` without introducing breaking changes.  --- ✨ Let Copilot coding agent [set things up for you](https://github.com/microsoft/onnxruntime/issues/new?title=✨+Set+up+Copilot+instructions&body=Configure%20instructions%20for%20this%20repository%20as%20documented%20in%20%5BBest%20practices%20for%20Copilot%20coding%20agent%20in%20your%20repository%5D%28https://gh.io/copilot-coding-agent-tips%29%2E%0A%0A%3COnboard%20this%20repo%3E&assignees=copilot) — coding agent works faster and does higher quality work when set up for your repo. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: fs-eire <7679871+fs-eire@users.noreply.github.com> * [webgpu] Optimize InstanceNormalization by removing redundant transpose (microsoft#26626) ### Description  This PR optimizes `InstanceNormalization` by removing redundant transpose. Given the implementation of `InstanceNormalization` for `NCHW` is more effiencient, we don't need to add wrapper `Transpose` to make it run in `NHWC`, which helps use to elide redundant transpose and improve performance. Testing on Lunar Lake shows about `~60%` performance improvement in `InstanceNormalization` operations. #### `InstanceNormalization` OP benchmark The input tensor shape: `(1,32,1048576)` The scale tensor shape: `(32)` The B tensor shape: `(32)` | time cost (ms) | baseline | opt | diff | | ---------------- | -------- | ---- | ---- | | Lunar Lake | 82.6 | 34.2 | 58% | #### Model benchmark | time cost (ms) | baseline | opt | diff | | ---------------- | -------- | ---- | ---- | | sd-turbo-vae-decoder-fp16-demo | 2437.6 | 1835.9 | 25% | ### Motivation and Context  Please see above * [webgpu] refactor a few "context" classes (microsoft#26602) ### Description This PR refactors a few "context" classes to make it clearer and support new features. --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> * Bump actions/checkout from 5 to 6 (microsoft#26641) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/releases">actions/checkout's releases</a>.</em></p> <blockquote> <h2>v6.0.0</h2> <h2>What's Changed</h2> <ul> <li>Update README to include Node.js 24 support details and requirements by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://github.com/actions/checkout/pull/2248">actions/checkout#2248</a></li> <li>Persist creds to a separate file by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2286">actions/checkout#2286</a></li> <li>v6-beta by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2298">actions/checkout#2298</a></li> <li>update readme/changelog for v6 by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2311">actions/checkout#2311</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v5.0.0...v6.0.0">https://github.com/actions/checkout/compare/v5.0.0...v6.0.0</a></p> <h2>v6-beta</h2> <h2>What's Changed</h2> <p>Updated persist-credentials to store the credentials under <code>$RUNNER_TEMP</code> instead of directly in the local git config.</p> <p>This requires a minimum Actions Runner version of <a href="https://github.com/actions/runner/releases/tag/v2.329.0">v2.329.0</a> to access the persisted credentials for <a href="https://docs.github.com/en/actions/tutorials/use-containerized-services/create-a-docker-container-action">Docker container action</a> scenarios.</p> <h2>v5.0.1</h2> <h2>What's Changed</h2> <ul> <li>Port v6 cleanup to v5 by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2301">actions/checkout#2301</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v5...v5.0.1">https://github.com/actions/checkout/compare/v5...v5.0.1</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/blob/main/CHANGELOG.md">actions/checkout's changelog</a>.</em></p> <blockquote> <h1>Changelog</h1> <h2>V6.0.0</h2> <ul> <li>Persist creds to a separate file by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2286">actions/checkout#2286</a></li> <li>Update README to include Node.js 24 support details and requirements by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://github.com/actions/checkout/pull/2248">actions/checkout#2248</a></li> </ul> <h2>V5.0.1</h2> <ul> <li>Port v6 cleanup to v5 by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2301">actions/checkout#2301</a></li> </ul> <h2>V5.0.0</h2> <ul> <li>Update actions checkout to use node 24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://github.com/actions/checkout/pull/2226">actions/checkout#2226</a></li> </ul> <h2>V4.3.1</h2> <ul> <li>Port v6 cleanup to v4 by <a href="https://github.com/ericsciple"><code>@ericsciple</code></a> in <a href="https://github.com/actions/checkout/pull/2305">actions/checkout#2305</a></li> </ul> <h2>V4.3.0</h2> <ul> <li>docs: update README.md by <a href="https://github.com/motss"><code>@motss</code></a> in <a href="https://github.com/actions/checkout/pull/1971">actions/checkout#1971</a></li> <li>Add internal repos for checking out multiple repositories by <a href="https://github.com/mouismail"><code>@mouismail</code></a> in <a href="https://github.com/actions/checkout/pull/1977">actions/checkout#1977</a></li> <li>Documentation update - add recommended permissions to Readme by <a href="https://github.com/benwells"><code>@benwells</code></a> in <a href="https://github.com/actions/checkout/pull/2043">actions/checkout#2043</a></li> <li>Adjust positioning of user email note and permissions heading by <a href="https://github.com/joshmgross"><code>@joshmgross</code></a> in <a href="https://github.com/actions/checkout/pull/2044">actions/checkout#2044</a></li> <li>Update README.md by <a href="https://github.com/nebuk89"><code>@nebuk89</code></a> in <a href="https://github.com/actions/checkout/pull/2194">actions/checkout#2194</a></li> <li>Update CODEOWNERS for actions by <a href="https://github.com/TingluoHuang"><code>@TingluoHuang</code></a> in <a href="https://github.com/actions/checkout/pull/2224">actions/checkout#2224</a></li> <li>Update package dependencies by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://github.com/actions/checkout/pull/2236">actions/checkout#2236</a></li> </ul> <h2>v4.2.2</h2> <ul> <li><code>url-helper.ts</code> now leverages well-known environment variables by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://github.com/actions/checkout/pull/1941">actions/checkout#1941</a></li> <li>Expand unit test coverage for <code>isGhes</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://github.com/actions/checkout/pull/1946">actions/checkout#1946</a></li> </ul> <h2>v4.2.1</h2> <ul> <li>Check out other refs/* by commit if provided, fall back to ref by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://github.com/actions/checkout/pull/1924">actions/checkout#1924</a></li> </ul> <h2>v4.2.0</h2> <ul> <li>Add Ref and Commit outputs by <a href="https://github.com/lucacome"><code>@lucacome</code></a> in <a href="https://github.com/actions/checkout/pull/1180">actions/checkout#1180</a></li> <li>Dependency updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>- <a href="https://github.com/actions/checkout/pull/1777">actions/checkout#1777</a>, <a href="https://github.com/actions/checkout/pull/1872">actions/checkout#1872</a></li> </ul> <h2>v4.1.7</h2> <ul> <li>Bump the minor-npm-dependencies group across 1 directory with 4 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://github.com/actions/checkout/pull/1739">actions/checkout#1739</a></li> <li>Bump actions/checkout from 3 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://github.com/actions/checkout/pull/1697">actions/checkout#1697</a></li> <li>Check out other refs/* by commit by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://github.com/actions/checkout/pull/1774">actions/checkout#1774</a></li> <li>Pin actions/checkout's own workflows to a known, good, stable version. by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://github.com/actions/checkout/pull/1776">actions/checkout#1776</a></li> </ul> <h2>v4.1.6</h2> <ul> <li>Check platform to set archive extension appropriately by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://github.com/actions/checkout/pull/1732">actions/checkout#1732</a></li> </ul> <h2>v4.1.5</h2> <ul> <li>Update NPM dependencies by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://github.com/actions/checkout/pull/1703">actions/checkout#1703</a></li> <li>Bump github/codeql-action from 2 to 3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://github.com/actions/checkout/pull/1694">actions/checkout#1694</a></li> <li>Bump actions/setup-node from 1 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://github.com/actions/checkout/pull/1696">actions/checkout#1696</a></li> <li>Bump actions/upload-artifact from 2 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://github.com/actions/checkout/pull/1695">actions/checkout#1695</a></li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/actions/checkout/commit/1af3b93b6815bc44a9784bd300feb67ff0d1eeb3"><code>1af3b93</code></a> update readme/changelog for v6 (<a href="https://github.com/actions/checkout/issues/2311">#2311</a>)</li> <li><a href="https://github.com/actions/checkout/commit/71cf2267d89c5cb81562390fa70a37fa40b1305e"><code>71cf226</code></a> v6-beta (<a href="https://github.com/actions/checkout/issues/2298">#2298</a>)</li> <li><a href="https://github.com/actions/checkout/commit/069c6959146423d11cd0184e6accf28f9d45f06e"><code>069c695</code></a> Persist creds to a separate file (<a href="https://github.com/actions/checkout/issues/2286">#2286</a>)</li> <li><a href="https://github.com/actions/checkout/commit/ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493"><code>ff7abcd</code></a> Update README to include Node.js 24 support details and requirements (<a href="https://github.com/actions/checkout/issues/2248">#2248</a>)</li> <li>See full diff in <a href="https://github.com/actions/checkout/compare/v5...v6">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/checkout&package-manager=github_actions&previous-version=5&new-version=6)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) 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> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * add LogEvaluationStart for ReplayGraph (microsoft#26645) ### Description  add LogEvaluationStart for ReplayGraph to match LogEvaluationStop ### Motivation and Context  So by using ETW, could capture run time correctly Co-authored-by: hualxie <hualxie@microsoft.com> * add LogCompileModel to mark the session usage (microsoft#26646) ### Description  add LogCompileModel to mark the session usage as Compile because that session will not be used for inference We could also use it to log compile model parameters if needed ### Motivation and Context  We are building a profiling tool for WinML and we want to differentiate Compile session and inference session. I think there are two ways to do it but I don't know which is better microsoft#26646 microsoft#26647 --------- Co-authored-by: hualxie <hualxie@microsoft.com> * [webgpu] Fix bug introduced by RoE (microsoft#26661) Fix bug introduced by microsoft#26563 which used the wrong condition by accident and results incorrect result in graph capture mode. * [QNN-EP] Enable verbose and artifacts saving in onnxruntime_provider_test.exe (microsoft#26396) ### Description  - The change allows users to better debug unit tests by adding the following environment variables: - `QNN_DUMP_ONNX`: Dump input onnx model - `QNN_DUMP_JSON`: Dump json qnn graph with provider_option `dump_json_qnn_graph` - `QNN_DUMP_DLC`: Dump dlc with provider_option `qnn_ir_backend_path` - `QNN_VERBOSE`: Use the log level `ORT_LOGGING_LEVEL_VERBOSE` - Developers can use the environment variables above to save the artifacts of QNN-EP testcases to a directory named with `<TestSuite>_<TestName>` ``` . ├── QnnCPUBackendTests_BatchNorm2D_fp32 # RunQnnModelTest │ ├── dumped_f32_model.onnx # float32 ONNX model │ ├── QNNExecutionProvider_QNN_XXXX_X_X.dlc │ └── QNNExecutionProvider_QNN_XXXX_X_X.json ├── QnnHTPBackendTests_BatchNorm_FP16 # TestFp16ModelAccuracy │ ├── dumped_f16_model.onnx # float16 ONNX model │ ├── dumped_f32_model.onnx # float32 ONNX model │ ├── QNNExecutionProvider_QNN_XXXX_X_X.dlc │ └── QNNExecutionProvider_QNN_XXXX_X_X.json └── QnnHTPBackendTests_BatchNorm2D_U8U8S32 # TestQDQModelAccuracy ├── dumped_f32_model.onnx # float32 ONNX model ├── dumped_qdq_model.onnx # QDQ ONNX model ├── QNNExecutionProvider_QNN_XXXX_X_X.dlc └── QNNExecutionProvider_QNN_XXXX_X_X.json # All artifact files are placed under the current working directory from which the test binary is invoked. ``` ### Motivation and Context  - The Json qnn graph/dlc are helpful for backend to debug performance/accuracy issues - By comparing the onnx and Json qnn graph/dlc, we can locate the issue about graph manipulation. * [webgpu] Use multiplication instead of pow if exponent is 2 (microsoft#26667) ### Description More accurately compute Pow(2.0) on WebGPU EP. Reproduction script: ```py from onnx import helper, TensorProto import onnxruntime as ort import numpy as np # 1. Create the ONNX model # Define input and output input_info = helper.make_tensor_value_info('X', TensorProto.FLOAT, [1, 1]) output_info = helper.make_tensor_value_info('Y', TensorProto.FLOAT, [1, 1]) # Create a constant tensor for the exponent (2.0) exponent_tensor = helper.make_tensor('exponent', TensorProto.FLOAT, [], [2.0]) exponent_node = helper.make_node('Constant', [], ['exponent_out'], value=exponent_tensor) # Create the Pow node # Pow takes two inputs: Base (X) and Power (exponent_out) pow_node = helper.make_node( 'Pow', inputs=['X', 'exponent_out'], outputs=['Y'], name='PowNode' ) # Create the graph graph_def = helper.make_graph( [exponent_node, pow_node], 'test-model', [input_info], [output_info] ) # Create the model model_def = helper.make_model(graph_def, producer_name='onnx-example') opset = model_def.opset_import[0] opset.version = 13 # Ensure opset version supports the operations # 2. Convert model to string (bytes) model_str = model_def.SerializeToString() # 3. Prepare input data np.random.seed(0) input_data = np.array([[-2e3]], dtype=np.float32) # 4. Run on CPUExecutionProvider sess_cpu = ort.InferenceSession(model_str, providers=['CPUExecutionProvider']) res_cpu = sess_cpu.run(['Y'], {'X': input_data})[0] print("CPU Result:", res_cpu) # 5. Run on WebGpuExecutionProvider sess_webgpu = ort.InferenceSession(model_str, providers=['WebGpuExecutionProvider']) res_webgpu = sess_webgpu.run(['Y'], {'X': input_data})[0] print("WebGPU Result:", res_webgpu) # Compare results diff = np.abs(res_cpu - res_webgpu) max_diff = diff.max().item() assert max_diff < 1e-5, f"Results do not match within tolerance! Max diff: {max_diff}" print("Results match!") ``` currently produces ``` CPU Result: [[4.e+06]] WebGPU Result: [[3.999999e+06]] --------------------------------------------------------------------------- AssertionError Traceback (most recent call last) Cell In[1], [line 56](vscode-notebook-cell:?execution_count=1&line=56) 54 diff = np.abs(res_cpu - res_webgpu) 55 max_diff = diff.max().item() ---> [56](vscode-notebook-cell:?execution_count=1&line=56) assert max_diff < 1e-5, f"Results do not match within tolerance! Max diff: {max_diff}" 57 print("Results match!") AssertionError: Results do not match within tolerance! Max diff: 1.0 ``` but with this PR: ``` CPU Result: [[4.e+06]] WebGPU Result: [[4.e+06]] Results match! ``` ### Motivation and Context Leads to downstream issues/inaccuracies for certain models, especially those which have larger values to compute pow(x,2) for. cc @guschmue * Avoid creation of temporary protobuf object (microsoft#26681) ### Description While profiling session creation time for large graphs (number of nodes, not size of tensors), we noticed that the creations and subsequent destructions of protobuf objects were the major hotspot. This PR avoids its creation. Signed-off-by: Christian Bourjau <christian.bourjau@quantco.com> * Use `std::string_view` directly as key to `absl::flat_hash_map::find` (microsoft#26682) ### Description Use `std::string_view` directly as key in `find` method of `flat_hash_map`. This part of the absl documentation may provide further insights: https://abseil.io/docs/cpp/guides/container#heterogeneous-lookup ### Motivation and Context We noticed this when profiling the session creation of large models (in terms of the number of nodes). Signed-off-by: Christian Bourjau <christian.bourjau@quantco.com> * [webgpu] Convert i32 to u32 in uniforms (microsoft#26676) In debug mode, `webgpu_context.cc:257 Run Uniform variable[5] (head_size) data type mismatch in program "SplitPackedQKVWithRotaryEmbeddingAndCopyKV", Expected: u32, Actual: i32`. No issue in release mode. Convert i32 to u32 to avoid this issue. * [webgpu] Fix BatchNormalization ShapeInferenceError for 2D inputs (microsoft#26659) ### Description Test model (happens with any 2D inputs): [2191__visual_projection_visual_projection.1_BatchNormalization.onnx.zip](https://github.com/user-attachments/files/23758390/2191__visual_projection_visual_projection.1_BatchNormalization.onnx.zip) Command: ``` python -c "import onnxruntime as ort; ort.InferenceSession('2191__visual_projection_visual_projection.1_BatchNormalization.onnx', providers=['WebGpuExecutionProvider'])" ``` Before (failure): ``` Op (BatchNormalization) [ShapeInferenceError] Tensor must have at least 3 dimensions to convert between channels first and channels last. ``` After (success): ``` (nothing, meaning success) ``` ### Motivation and Context This fixes BatchNormalization on WebGPU, matching CPU version. cc @guschmue * Clear cuda error on unsupported CudaMemPool test (microsoft#26629) ### Description  CudaMemPool test checks if it is supported in a given environment. We need to clear the error not to affect subsequent tests. ### Motivation and Context  Potential test failure. * [QNN-EP] Include detailed error message in the returned status (microsoft#26546) ### Description  The original error message only shows: "Failed to setup QNN input tensors for graph: <graph_name>" This change adds more detailed error information by logging the failure reason from [SetupTensors](https://github.com/microsoft/onnxruntime/blob/ea55c160a36d658eae61a4c7aeda6cb55dd54dec/onnxruntime/core/providers/qnn/builder/qnn_model.cc#L386), making it easier to debug issues. ### Motivation and Context  User requires detailed error logging for the ORT online context binary generation. * add support for int32_t in webgpu / slice (microsoft#26693) fix for microsoft#26690 * [webgpu] Remove `global_id` and `workgroup_id` in gemm_utils.cc (microsoft#26662) ### Description This patch replaces `global_id` and `workgroup_id` with `logical_global_id` and `logical_workgroup_id` which are computed from `workgroup_idx` and the dispatch workgroup sizes set in `ProgramBase::SetDispatchGroupSize()`. ### Motivation and Context We shouldn't use `global_id` or `workgroup_id` directly because the dispatch workgroup sizes may be normalized in `ProgramManager::NormalizeDispatchGroupSize()`. * [webgpu] Correct definition of large numbers, fixes softmax(max_negative_number) in float32 (microsoft#26670) ### Description The correct definition of the most negative number is `-3.40282346638528e+38`, according to IEEE 754, but it is being incorrectly registered inline as a truncated version `-3.402823e+38f`. ```py >>> import numpy as np >>> np.finfo(np.float32).min np.float32(-3.4028235e+38) >>> np.finfo(np.float32).min.item() -3.4028234663852886e+38 ``` For this reason, values less than this threshold were handled incorrectly. While this may seem like a small/irrelevant detail, it's essential in attention masking, where we do in fact use this value, leading to large numerical errors down the line. Reproduction: ```py from onnx import helper, TensorProto import onnxruntime as ort import numpy as np # 1. Create the ONNX model # Define input and output input_shape = [1, 2] input_info = helper.make_tensor_value_info('X', TensorProto.FLOAT, input_shape) output_info = helper.make_tensor_value_info('Y', TensorProto.FLOAT, input_shape) # Create the Softmax node # Softmax takes one input: X softmax_node = helper.make_node( 'Softmax', inputs=['X'], outputs=['Y'], name='SoftmaxNode', axis=-1 # Default axis is -1, usually applied to the last dimension ) # Create the graph graph_def = helper.make_graph( [softmax_node], 'test-model', [input_info], [output_info] ) # Create the model model_def = helper.make_model(graph_def, producer_name='onnx-example') opset = model_def.opset_import[0] opset.version = 13 # Ensure opset version supports the operations # 2. Convert model to string (bytes) model_str = model_def.SerializeToString() # 3. Prepare input data np.random.seed(0) input_data = np.array( [[-3.40282346638528e+38, -3.40282346638528e+38]] # [[-3.4028234663852886e+38, -3.4028234663852886e+38]] ).astype(np.float32) print(input_data.tolist()) # 4. Run on CPUExecutionProvider sess_cpu = ort.InferenceSession(model_str, providers=['CPUExecutionProvider']) res_cpu = sess_cpu.run(['Y'], {'X': input_data})[0] print("CPU Result:", res_cpu) # 5. Run on WebGpuExecutionProvider sess_webgpu = ort.InferenceSession(model_str, providers=['WebGpuExecutionProvider']) res_webgpu = sess_webgpu.run(['Y'], {'X': input_data})[0] print("WebGPU Result:", res_webgpu) # Compare results diff = np.abs(res_cpu - res_webgpu) max_diff = diff.max().item() print(diff) print(f"Max diff: {max_diff}") assert max_diff < 1e-5, f"Results do not match within tolerance! Max diff: {max_diff}" print("Results match!") ``` Before: ``` [[-3.4028234663852886e+38, -3.4028234663852886e+38]] CPU Result: [[0.5 0.5]] WebGPU Result: [[0. 0.]] [[0.5 0.5]] Max diff: 0.5 AssertionError: Results do not match within tolerance! Max diff: 0.5 ``` After: ``` [[-3.4028234663852886e+38, -3.4028234663852886e+38]] CPU Result: [[0.5 0.5]] WebGPU Result: [[0.5 0.5]] [[0. 0.]] Max diff: 0.0 Results match! ``` cc @guschmue * [TRT/TRT RTX EP] Fix bug for missing outputs in the returning ComputeCapability/IndexedSubGraph (microsoft#26444) ### Description For TRT EP's `GetCapability()`, in some case, the `GetSubGraph()` won't add graph's output to the `ComputeCapability/IndexedSubGraph` returning to ORT. The issue if from following code: ````c++ ... if (node->GetOutputEdgesCount() > node->OutputDefs().size()) { ... // execute here } else { ... if (graph_output_names.find(output->Name()) != graph_output_names.end()) { graph_outputs_to_add[output] = output_order; // missing this } } ```` Update TRT RTX EP as well. ### Motivation and Context microsoft#25373 * [ROCM] Remove docker, contrib ops, ci scripts related to ROCM EP (microsoft#26697) ### Description This is follow up of microsoft#25181 to remove ROCM EP related files to avoid confusion. Documents will be updated later. ### Motivation and Context microsoft#26692 --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Christian Bourjau <christian.bourjau@quantco.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: fs-eire <7679871+fs-eire@users.noreply.github.com> Co-authored-by: Wenqin Yang <wenqin.yang@intel.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: xieofxie <xieofxie@126.com> Co-authored-by: hualxie <hualxie@microsoft.com> Co-authored-by: Jiajia Qin <jiajiaqin@microsoft.com> Co-authored-by: qti-hungjuiw <hungjuiw@qti.qualcomm.com> Co-authored-by: Joshua Lochner <admin@xenova.com> Co-authored-by: Christian Bourjau <cbourjau@users.noreply.github.com> Co-authored-by: Xiaofei Han <xiaofeihan@microsoft.com> Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: chunghow-qti <chunghow@qti.qualcomm.com> Co-authored-by: Guenther Schmuelling <guschmue@microsoft.com> Co-authored-by: Jiawei Shao <jiawei.shao@intel.com> Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com> Co-authored-by: Tianlei Wu <tlwu@microsoft.com>

### Description This PR refactors a few "context" classes to make it clearer and support new features. --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>

fs-eire mentioned this pull request Nov 19, 2025

Add weight layout transformation cache for Conv operator #26595

Closed

fs-eire force-pushed the fs-eire/ex-compute-context branch 2 times, most recently from 0a89439 to db4badb Compare November 21, 2025 02:11

fs-eire changed the title ~~[webgpu] update ComputeContext to make it work with PrePack~~ [webgpu] refactor a few "context" classes Nov 21, 2025

[webgpu] refactor of a few context classes

19e2d51

fs-eire force-pushed the fs-eire/ex-compute-context branch from db4badb to 19e2d51 Compare November 21, 2025 09:32

Merge remote-tracking branch 'microsoft/main' into fs-eire/ex-compute…

169b056

…-context

fs-eire marked this pull request as ready for review November 24, 2025 17:32

fs-eire requested review from Copilot and qjia7 November 25, 2025 00:17

Copilot started reviewing on behalf of fs-eire November 25, 2025 00:18 View session

Copilot finished reviewing on behalf of fs-eire November 25, 2025 00:22

Copilot AI reviewed Nov 25, 2025

View reviewed changes

onnxruntime/core/providers/webgpu/webgpu_kernel.h Show resolved Hide resolved

onnxruntime/core/providers/webgpu/webgpu_kernel.h Show resolved Hide resolved

onnxruntime/core/providers/webgpu/nn/conv.h Outdated Show resolved Hide resolved

Update onnxruntime/core/providers/webgpu/nn/conv.h

77b22ea

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Copilot AI mentioned this pull request Nov 25, 2025

Add documentation for PrePack and PrePackInternal methods in WebGpuKernel #26650

Merged

Copilot AI mentioned this pull request Nov 25, 2025

Add documentation for PrePack and PrePackInternal methods in WebGpuKernel #26651

Closed

fs-eire requested a review from Copilot November 25, 2025 00:41

Copilot started reviewing on behalf of fs-eire November 25, 2025 00:42 View session

Copilot finished reviewing on behalf of fs-eire November 25, 2025 00:43

Copilot AI reviewed Nov 25, 2025

View reviewed changes

onnxruntime/core/providers/webgpu/compute_context.cc Show resolved Hide resolved

onnxruntime/core/providers/webgpu/compute_context.cc Show resolved Hide resolved

qjia7 reviewed Nov 25, 2025

View reviewed changes

onnxruntime/core/providers/webgpu/nn/conv.cc Show resolved Hide resolved

onnxruntime/core/providers/webgpu/nn/conv.cc Show resolved Hide resolved

qjia7 approved these changes Nov 26, 2025

View reviewed changes

fs-eire merged commit 5c28c7e into main Nov 26, 2025
97 of 101 checks passed

fs-eire deleted the fs-eire/ex-compute-context branch November 26, 2025 03:18

qjia7 mentioned this pull request Nov 26, 2025

[webgpu] Optimize Conv by im2col-matmul #26603

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[webgpu] refactor a few "context" classes#26602

[webgpu] refactor a few "context" classes#26602
fs-eire merged 4 commits intomainfrom
fs-eire/ex-compute-context

fs-eire commented Nov 19, 2025 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI commented Nov 25, 2025

Uh oh!

Copilot AI commented Nov 25, 2025

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

fs-eire commented Nov 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI commented Nov 25, 2025

Uh oh!

Copilot AI commented Nov 25, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

fs-eire commented Nov 19, 2025 •

edited

Loading