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
cb7e19cebc936d580389197559a4717ac2006c65b1ccbf4bda34c75d1bbf8c58	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	04/10/2026 12:35 PM UTC
8e49ed2aa085d0389d63160e27139a8390d0075bf1441fec93bc82204451c220	ARG	`NVIDIA_BUILD_REF=c9cbd3a6f46587fcce010740e6c055da7ddc2506`	04/10/2026 12:35 PM UTC
f23e4c7f16bd080588d1ef194e5114858d9a356a173ad04dee8b3e321f532e56	LABEL	`com.nvidia.build.id=295860571`	04/10/2026 12:35 PM UTC
5d75387a15264cfa17611d780786f2e46e113639bacb560f569008e34aad2b26	ENV	`NVIDIA_BUILD_ID=295860571`	04/10/2026 12:35 PM UTC
b1c5e15c38eb612f7cd39a948cf0c9ea438bd49cca7484e47d05185f0f3fa4aa	ARG	`NVIDIA_BUILD_ID=295860571`	04/10/2026 12:35 PM UTC
b15648fa85d4bd7bd8144aaff51985e348b41efa71952d3e83eb6e3846b88f3f	ENV	`NVIDIA_VLLM_VERSION=26.03.post1`	04/10/2026 12:35 PM UTC
f66baa330101320740c5d00842d8cfd71c6c7ba5413d705eac38977f37eb64e0	ARG	`NVIDIA_VLLM_VERSION=26.03.post1`	04/10/2026 12:35 PM UTC
eece40f2832224e608b65983b3cae786c1fbc87b8db3bb227f0523d741947b81	LABEL	`com.nvidia.vllm.version=0.17.1+bd67d66a`	04/10/2026 12:35 PM UTC
005a810448e3d8de9762873dc1ed12d29b1b622e838a6761400e8195b758fc44	ENV	`PATH=/usr/local/lib/python3.12/dist-packages/torch_tensorrt/bin:/usr/local/cuda/bin:/usr/local/nixlbench/bin:/usr/local/nixl/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`	04/10/2026 12:35 PM UTC
62665166868d57aeda02bbfbecdaae3dcd52e262a09699defdb542015197f48e	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	04/10/2026 12:35 PM UTC