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
642c5e4883dd7c0984bc194840adb2e1d7d5583fcdf6140f69f314b5e11d0cb4	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	05/08/2026 4:28 AM UTC
b8254848b4faf96a3d9f82d96e67c6b8e4abc83d387e23c97eb87de2dff4f369	ARG	`NVIDIA_BUILD_REF=0434c12d637394e8ad22fa783207a699951528af`	05/08/2026 4:28 AM UTC
691f132a4e4061007170562b88f7387500bd7f66e4f9c8347392cf5bf4ec0c36	LABEL	`com.nvidia.build.id=313685830`	05/08/2026 4:28 AM UTC
65dad52593f341a5d70a52be99a79b0638dd66a291a66b8d1a5a6a093f58ebdc	ENV	`NVIDIA_BUILD_ID=313685830`	05/08/2026 4:28 AM UTC
30c611e6f24d516864724aea941eb0eed26668e93ef7956e0d1a36860f7d9682	ARG	`NVIDIA_BUILD_ID=313685830`	05/08/2026 4:28 AM UTC
443d3755080e118044af93c14ca36e41f0897f4fb745465f35017357dee716eb	ENV	`NVIDIA_VLLM_VERSION=26.05`	05/08/2026 4:28 AM UTC
9cd76d545dcf87168edf7715ac9a2d97e00cb568bf169fffa7b225fd8ce4302d	ARG	`NVIDIA_VLLM_VERSION=26.05`	05/08/2026 4:28 AM UTC
bbf25ef855a3c5a629bb456efd243e07dd7cd24f7aa68d6446029f8b904ba55d	LABEL	`com.nvidia.vllm.version=0.20.1+7124b12a`	05/08/2026 4:28 AM UTC
7e2a2a9805041fb243d08547ba3f2a89f00599b3c1eac19cf7de4c0cebc5b49c	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`	05/08/2026 4:28 AM UTC
5f891eb5eb9a6324e3e2563c56710c9a67df030651f9b347137451eeac9c021c	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	05/08/2026 4:28 AM UTC