vLLM | NVIDIA NGC

NVIDIA

vLLM

Container

NVIDIA

vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. The NVIDIA vLLM NGC Container is optimized for GPU acceleration, and contains a validated set of libraries that enable and optimize GPU performance.

Layer	Label		Created
2233d24f75dfd7507c3859f58c1e876fdb100bedfe972964ab27a4c1e48480ed	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	11/08/2025 8:18 AM UTC
428296c5a84aad0288b07fa8d965cb976ad58df09c2dd6cd8cdedb839399d14e	ARG	`NVIDIA_BUILD_REF=70a7e4b3c87282a4cb66684ed2ae82174aa991a2`	11/08/2025 8:18 AM UTC
72f070ef6dc6e5a2f888019629c16874cb8f67939861382705f4b9fba72fba12	LABEL	`com.nvidia.build.id=231063343`	11/08/2025 8:18 AM UTC
5739b51b0ba60cd2e36322c56b4989c34c21360e6f446a4e5cba0e171236127b	ENV	`NVIDIA_BUILD_ID=231063343`	11/08/2025 8:18 AM UTC
3f6cdbf3e39d6fec8a55e56cf67e90892e47218c2c284f0813d89cb772a13cb8	ARG	`NVIDIA_BUILD_ID=231063343`	11/08/2025 8:18 AM UTC
1712435d82124370fc1e71ae15acf75ed4f4ac295ac6cd3d0a20773159e932df	ENV	`NVIDIA_VLLM_VERSION=25.11`	11/08/2025 8:18 AM UTC
2e7abe82f71eeee4b67d7b5ee52c46b7cd0d0d3305aa19f198ffe1ded87a7b09	ARG	`NVIDIA_VLLM_VERSION=25.11`	11/08/2025 8:18 AM UTC
382e5f743c46df74aa87df1007062bbdf154bf873246ce299db50476eba7b673	LABEL	`com.nvidia.vllm.version=0.11.0+582e4e37`	11/08/2025 8:18 AM UTC
045fec00cc7f652c228459b5b9601182e7ef2a7c7a82b3d7e077301e65454ced	ENV	`PATH=/usr/local/lib/python3.12/dist-packages/torch_tensorrt/bin:/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin:/opt/tensorrt/bin`	11/08/2025 8:18 AM UTC
c84897ee8734c932c110005dd16e4e9d557f173984286e03712581d3c7ed6c1b	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	11/08/2025 8:18 AM UTC