NVIDIA NIM for LLM/VLM 2.1.6 Released: Five Models Enter Mainline Containers, Backend Upgraded to vLLM 0.32.0 & SGLang 0.5.22
AI-generated summary NVIDIA has shipped version 2.1.6 of its NIM for LLM/VLM inference containers with upgraded backends and security fixes. The release promotes five models to mainline containers and introduces cached runtime manifests for faster restarts.