onnxruntime

b75bfe16 - Fix WebGPU ConvTranspose bias validation in TypeScript and C++ implementations (#27213)

Fix WebGPU ConvTranspose bias validation in TypeScript and C++ implementations (#27213) ### Description WebGPU EP's ConvTranspose operator failed to properly validate bias tensor shape in both TypeScript and C++ implementations. Undefined `group` attribute caused NaN in validation checks, allowing invalid bias tensors to pass. **TypeScript Changes** (`js/web/lib/wasm/jsep/webgpu/ops/conv-transpose.ts`): - **Parse time default**: Set `group` to 1 when undefined (line 135 in `parseConvTransposeAttributes`) ```typescript const group = (attributes.group as number) ?? 1; // per ONNX spec ``` - **Enhanced bias validation** (lines 182-192 in `validateInputs`): - Check bias is 1D before accessing dimensions - Validate bias size matches output channels: `weight.dims[1] * group` - Descriptive errors showing actual vs expected values ```typescript if (inputs.length === 3) { if (inputs[2].dims.length !== 1) { throw new Error('invalid bias: bias must be 1D tensor'); } const featureMaps = inputs[1].dims[1] * attributes.group; if (inputs[2].dims[0] !== featureMaps) { throw new Error( `invalid bias: bias size (${inputs[2].dims[0]}) must be equal to output channels (${featureMaps})`, ); } } ``` **C++ Changes** (`onnxruntime/core/providers/webgpu/nn/conv_transpose.cc`): - **Added bias validation** (lines 61-71 in `ComputeInternal`): - Validates bias is 1D tensor - Validates bias size matches output channels (`num_output_channels = group * filter_shape[1]`) - Uses consistent error messages with TypeScript implementation ```cpp // Validate bias shape if provided if (has_bias) { const auto& bias_shape = bias->Shape(); if (bias_shape.NumDimensions() != 1) { return ORT_MAKE_STATUS(ONNXRUNTIME, INVALID_ARGUMENT, "invalid bias: bias must be 1D tensor"); } if (bias_shape[0] != num_output_channels) { return ORT_MAKE_STATUS(ONNXRUNTIME, INVALID_ARGUMENT, "invalid bias: bias size (", bias_shape[0], ") must be equal to output channels (", num_output_channels, ")"); } } ``` **Code Formatting**: - Applied prettier formatting to ensure TypeScript code adheres to project style guidelines (120 character line width, proper line breaks for long error messages) ### Motivation and Context Addresses issue where tests with intentionally invalid bias shapes were incorrectly passing in the WebGPU EP. The fix ensures: - Invalid bias shapes are properly rejected in both TypeScript and C++ implementations - NaN bugs prevented across all code paths using `group` attribute in TypeScript - Clear error messages for debugging - Consistent validation logic across both WebGPU backend implementations - Code passes all linting and formatting checks Note: The C++ implementation already handles `group` attribute defaulting to 1 in the ConvAttributes base class, so only bias validation needed to be added. <!-- START COPILOT ORIGINAL PROMPT --> <details> <summary>Original prompt</summary> > > ---- > > *This section details on the original issue you should resolve* > > <issue_title>[Web] WebGPU EP's ConvTranspose input validation seems loose</issue_title> > <issue_description>### Describe the issue > > As title. > > The WebGPU EP's ConvTranspose operator neglects to check if the bias is of the expected shape. See tests added in https://github.com/microsoft/onnxruntime/pull/27209. The WebGPU EP "passes" those tests when a failure of some sort is expected (preferably along the lines of bias is not of the expected shape). Not sure if this is masking a bug of some sort. > > ### To reproduce > > Run tests in https://github.com/microsoft/onnxruntime/pull/27209 with the WebGPU EP > > ### Urgency > > Not urgent > > ### ONNX Runtime Installation > > Built from Source > > ### ONNX Runtime Version or Commit ID > > Run tests in PR branch https://github.com/microsoft/onnxruntime/pull/27209 > > ### Execution Provider > > 'webgpu' (WebGPU)</issue_description> > > ## Comments on the Issue (you are @copilot in this section) > > <comments> > </comments> > </details> <!-- START COPILOT CODING AGENT SUFFIX --> - Fixes microsoft/onnxruntime#27210 <!-- START COPILOT CODING AGENT TIPS --> --- 💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more [Copilot coding agent tips](https://gh.io/copilot-coding-agent-tips) in the docs. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: guschmue <22941064+guschmue@users.noreply.github.com> Co-authored-by: Guenther Schmuelling <guschmue@microsoft.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>