Ops, Tuning & Troubleshooting
Bring-up steps, validation checks, and performance levers.
Bring-Up Procedure
curl -s http://127.0.0.1:8000/v2/health/ready
curl -s http://127.0.0.1:8080/v1/.well-known/ready
docker logs -f finisher-app
nvidia-smi ; nvidia-smi topo -m
lsmod | grep nvidia_peermem ; ibv_devinfo