Serving & Orchestration
NVIDIA NIM
nvidiaPrebuilt, optimized inference microservice containers wrapping TensorRT-LLM, vLLM, or Triton behind a standardized API — runs via Docker or Kubernetes (not K8s-exclusive; most other nodes in this column are commonly K8s-deployed too)
Editorial compatibility: these components can be used together in representative deployments. That's not a requirement or a validated implementation. For real deployments, see the sourced reference architectures.