[Mustapha Jaber (mustjab)]

Summary

Follow-up to the review of #33110.

The shared WebGPU data-transfer wrapper does not need to own a context. A session stream already supplies its owning execution provider's transfer state, while a streamless copy can select its registered context from the GPU tensor's memory-device ID.

• Remove the cached context, initialization mutex, and context-ID argument from the internal transfer creator.
• Route session copies directly through their stream. Retain the tensor-selected registered context only for each streamless copy, including context zero, and flush successful streamless GPU-to-GPU copies.
• Document that memory-device identity does not register Dawn objects, the current Env/global allocator context-zero restriction, and the registration requirements for external-context copies.

Allocator/session context IDs and the public C API are unchanged. This does not add pre-session external-context registration.

Validation

• Scoped C++ lintrunner and staged whitespace checks passed.
• Fresh Windows x64 Release external-Dawn plugin build on upstream main 864d87126864c64651f58a9b51d9006ad71b2c78 passed.
• All five native-host modes passed against the fresh ORT/plugin DLLs: baseline, host-device, missing-sync, callback-failure, and missing-proc-table. The host executable was reused after verifying its source was unchanged.
• Host-device coverage includes coexisting default/external context allocation and transfers, shader-cache reuse/isolation, and device usability after ORT teardown. Negative modes rejected invalid inputs or contained callback failures as expected.
• The same follow-up also passed the five host modes in both built-in and plugin configurations before rebasing onto current main.

[Copilot]

🟢 Approval recommended

The stateless lifecycle and routing changes are internally consistent and covered by existing multi-context transfer validation.

0 open findings

What changed in this PR

Makes shared WebGPU transfers stateless while preserving context-correct routing and lifecycle behavior.

Changes:

• Routes session copies through their WebGPU streams.
• Retains tensor-selected contexts only during streamless copies and flushes GPU-to-GPU copies.
• Documents external-context registration requirements.

No actionable findings identified.

File	Description
webgpu_provider_factory.cc	Removes cached transfer context and implements per-copy routing.
webgpu_provider_factory_creator.h	Updates the internal transfer creator contract.
ep/​factory.cc	Adopts the context-free creator.
WebGPU_External_Dawn.md	Documents memory identity and context registration constraints.

🧠 Review effort: Balanced

---

💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.