fix(provisioning): recover from vLLM readiness timeout and increase poll window

When create timed out during vLLM readiness polling (common for large
models like Qwen3.6-27B-FP8), rerunning create would stop and restart
the already-running container, restarting the whole startup sequence.

Now the vLLM install script checks if the container is already running
and serving the correct model before touching it. If it detects a
healthy container, it skips the stop/pull/start cycle entirely.

Also increases the readiness timeout from 20 min (240x5s) to 30 min
(360x5s) to accommodate cold starts with model download and CUDA graph
capture on large models.

0 files changed, 0 insertions, 0 deletions