Non-leader worker initialization failure can wedge MPI ranks

Description

When worker_main fails while constructing GenerationExecutorWorker on a non-leader rank, that rank returns while rank 0 can remain blocked in an MPI collective that the failed rank can no longer enter. The executor process then remains wedged instead of failing promptly, so the serving worker may require manual termination.

Proposed fix

Abort the MPI communicator from a non-leader rank when worker initialization raises. Rank 0 retains the existing behavior of reporting the initialization exception through worker_init_status_queue.

Validation

• Focused unit regression covering the non-leader failure path.
• Real 4-rank MPI integration test with rank 3 constructor failure: rank 3 invoked MPI_Abort, and the MPI job exited with code 1 before a 20-second timeout.

This was originally observed with disaggregated TensorRT-LLM serving, where a rank initialization failure otherwise left the node-level worker wedged.

Start by locating worker_main and the GenerationExecutorWorker construction path, then trace how non-leader ranks participate in the MPI collective and how rank 0 reports through worker_init_status_queue. Add a focused regression for non-leader initialization failure and run the real 4-rank MPI validation. Done means the failed rank aborts the communicator while rank 0 retains its existing reporting behavior and the job exits promptly.