[WebGPU EP] Support uint8 for Reshape

[miaobin]

Description

Adds uint8 data type support to the Reshape operator in the WebGPU execution provider. The op is used by detr-resnet-50 and other models that reshape uint8 tensors.

Motivation and Context

Adds uint8 to the WebGPU Reshape type constraint so uint8 Reshape nodes stop falling back to the CPU EP. Reshape is a pure copy/view op (it aliases the input buffer, or does a raw byte copy when not in-place) and never interprets element values in a shader, so uint8 is enabled unconditionally in both the versioned and latest-opset kernel factories -- no shader changes are needed.

This PR also adds a WebGPU uint8 Reshape test. It runs on a WebGPU-only session with CPU-EP fallback disabled (kOrtSessionOptionsDisableCPUEPFallback), so the node must be placed on the WebGPU kernel.

[azure-pipelines]

Azure Pipelines:
There may be pipelines that require an authorized user to comment /azp run to run.

[miaobin]

@hariharans29, PTAL, thanks!
cc/ @huningxin @ibelem @adrastogi

[Copilot]

Pull request overview

This PR extends the WebGPU Execution Provider’s Reshape kernel registration to accept uint8 tensors so Reshape nodes on uint8 data don’t fall back to CPU, and adds a regression test to ensure the WebGPU kernel is actually selected when CPU fallback is disabled.

Changes:

• Add uint8 to the WebGPU Reshape type constraints (both versioned and latest kernel factories).
• Add a WebGPU uint8 Reshape test that disables CPU-EP fallback to ensure proper EP placement.

Show a summary per file

File	Description
onnxruntime/test/providers/cpu/tensor/tensor_op_test.cc	Adds a uint8 Reshape test intended to force WebGPU execution by disabling CPU fallback.
onnxruntime/core/providers/webgpu/tensor/reshape.cc	Adds uint8 to the registered WebGPU Reshape type constraints.

Review details

• Files reviewed: 2/2 changed files
• Comments generated: 1
• Review effort level: Low

[hariharans29]

Please take a look at copilot's comment

[miaobin]

Please take a look at copilot's comment

Resolved the comment and please take another look, thanks a lot!

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (1)

onnxruntime/core/providers/webgpu/tensor/reshape.cc:45

• Same issue here: type_constraints can be moved into TypeConstraint to avoid copying the vector again during kernel registration.

  std::vector<MLDataType> type_constraints = GetOpTypeConstraints(enable_int64, true);
  type_constraints.push_back(DataTypeImpl::GetTensorType<uint8_t>());

  KernelCreatePtrFn kernel_create_fn = [](FuncManager&, const OpKernelInfo& info, std::unique_ptr<OpKernel>& out) -> Status {
    out = std::make_unique<Reshape>(info);

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated no new comments.