init: first impliment for async GPU connector

[specture724]

Purpose

Impliment an async GPU connector based on NVSHMEM.

Issue

• Related issue(s): [RFC]: Async GPU Connector #233
• Closing keyword, only if fully resolved: Closes [RFC]: Async GPU Connector #233

Scope

• In scope: GPU connectors, model runners, models
• Out of scope: NPU connectors

Test Plan

test_async_gpu_connector.py is the main unit test added. async_gpu_connector_e2e.py is for e2e GPU test. 1a1f and 2a2f eager recipe added.

Test Result

TBD

Docs Impact

• Files updated: TODO add docs for design
• If none, reason:

---

Essential PR Checklist

• Purpose is clear and linked to public context when possible.
• Scope is bounded.
• Compatibility with vLLM v0.26.0 is considered.
• No changes are made to the vLLM source checkout.
• Plugin-owned classes or explicit dotted class paths are preferred over monkey patches.
• Any compat shim or monkey patch is isolated, idempotent, version-guarded, documented, and tested.
• Imports remain CPU-safe; CUDA-heavy work is delayed or GPU-gated.
• Validation evidence is included, including skipped GPU tests when applicable.
• Documentation impact is stated.