vLLM's engine handshake made an untimed collective RPC that killed healthy single-DP engines.

PR #57226 removes a blocking collective_rpc from the handshake. EngineCoreProc._make_ready_response() called Executor.supports_draft_weight_updates() with no timeout before ready_event.set(), while __init__ waited on that event with a fixed 10-second timeout; at data_parallel_size=1 the first expiry raised a bare AssertionError and killed an engine whose workers were all alive and idle, with the front end reporting the empty message Failed core proc(s): {}. Observed on 8-GPU ROCm runs. The executor is now consulted only when weight transfer is actually configured.