nvidia-nim

NVIDIA NIM — independent third-party profile of a public API surface, by API Evangelist. NVIDIA NIM (NVIDIA Inference Microservices) is a catalog of GPU-accelerated, containerized AI inference microservices that package optimized model engines (TensorRT-LLM, vLLM, SGLang, Triton) behind industry-standard OpenAI-compatible REST APIs.

GitHub

Official source

Start locally with the CLI guide