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
245cedf13410718834a521871c4f635a3987fff8c745c01bdcb9e3ff9ee95ae5	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	12/23/2025 2:19 PM UTC
333434f88dafa75d0c0ea93a9261f302cf655aac8bd4d874d25825ef33ddb95a	ARG	`NVIDIA_BUILD_REF=ea9ed78162579d58e20db3b31cc7e0c7a263fc1b`	12/23/2025 2:19 PM UTC
5231303b31d6f87e00cd2b4d6d20ee0ea33ad94b4b3c8997661616fbb82fff92	LABEL	`com.nvidia.build.id=247811355`	12/23/2025 2:19 PM UTC
80812a4be4ba407d2aa69495ee7e5364b4866115c790350fee34b9aeef952725	ENV	`NVIDIA_BUILD_ID=247811355`	12/23/2025 2:19 PM UTC
8cd13ff78205dd15f7a0f360067eab19aba052108c19b61915e942cbf0056b3d	ARG	`NVIDIA_BUILD_ID=247811355`	12/23/2025 2:19 PM UTC
30a447230a36b89167db88e66e2543d468e82442ee9abbcdacace40be1fa415c	ENV	`NVIDIA_VLLM_VERSION=25.12.post1`	12/23/2025 2:19 PM UTC
7f5aa9e570e8db5789d3a5fbf949a0fcbaa8b85ac956abd2c3fabeb7417b9c96	ARG	`NVIDIA_VLLM_VERSION=25.12.post1`	12/23/2025 2:19 PM UTC
a2a228d18781a5a6e1606dc62157710f1616164e41081a82444758cc885bd361	LABEL	`com.nvidia.vllm.version=0.12.0+35a9f223`	12/23/2025 2:19 PM UTC
13b4f8ca66d5e99f98bb981b9908b27c65e3ca9cba2f6f8381ea41da06fcfe01	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`	12/23/2025 2:19 PM UTC
72c825f2c0e67a1616e6e5f07fca87ae58c6c5ff8a3cc67abc2e12215e2126d1	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	12/23/2025 2:19 PM UTC