fix: increase vLLM RPC timeout to 10 min for first-request JIT

First inference triggers Triton/TileLang kernel JIT compilation (2-3 min).
The default 5-min RPC timeout kills the engine. Bumped to 10 min via
VLLM_RPC_TIMEOUT_MS so the first request survives compilation.

Not ideal — would prefer to warm up the kernels during startup.
But CUDA graphs don't work well with grouped GEMMs and variable
expert counts. Will investigate vLLM warmup shape config later.

docker-compose.yml

@@ -9,6 +9,7 @@ services:
       - OMP_NUM_THREADS=128
       - CUDA_LAUNCH_BLOCKING=0
       - PYTHONUNBUFFERED=1
+      - VLLM_RPC_TIMEOUT_MS=600000
     command:
       - /model
       - --trust-remote-code