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
dbe1f51bc4f6eaa89806d29c3160d12e4091f3b16a7f21acda62fa730dfcb218	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace; ExposedPorts 6006/tcp, 8888/tcp`	09/27/2025 6:37 AM UTC
e897dcb3b1ce66ffc6f63650f2db0f7144bed6343645d4bec055a1a3225c679c	ARG	`NVIDIA_BUILD_REF=4b72d8148f9ffe067ac468dda616d07613a4db62`	09/27/2025 6:37 AM UTC
ecbe082f11cd1508729438225917390548111ee5e190924b3e34c8e742b6d3cd	LABEL	`com.nvidia.build.id=214638689`	09/27/2025 6:37 AM UTC
92113a5b56fd7074021bda45b9a8417765177ae79a6260f042a4199bc260b66f	ENV	`NVIDIA_BUILD_ID=214638689`	09/27/2025 6:37 AM UTC
cd75c2f4e3db8a870deb370cf1a2735deb0e56a0a03d1a56f044faca6cc71293	ARG	`NVIDIA_BUILD_ID=214638689`	09/27/2025 6:37 AM UTC
08549f402032f904a15d80b2291bcc413719626ca0b74cb97b5a45639c8ae2d1	ENV	`NVIDIA_VLLM_VERSION=25.09`	09/27/2025 6:37 AM UTC
6a4eb04b36d97959505e0b30c2ae06d46636328f9e02d11788bb412234840260	ARG	`NVIDIA_VLLM_VERSION=25.09`	09/27/2025 6:37 AM UTC
6fd27ea1d3d1c1b5f772a05d201844bd1e5daf9db6e8ae12ef083d0b54fbcac8	LABEL	`com.nvidia.vllm.version=0.10.1.1+381074ae`	09/27/2025 6:37 AM UTC
eb89f75c38a2ce78022599f46e745bd2c9641f944346ba1a20e519f15e900e56	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	09/27/2025 6:37 AM UTC
fe65b6c1de028cb33205dfb1ce1d53da8547f400898d9cb165ca10c5c766d96f	RUN	`TARGETARCH=amd64 VLLM_VERSION=0.10.1.1+381074ae sed -i -E 's/^([[:space:]]*)from \.modeling_utils import PreTrainedAudioTokenizerBase/\1pass/' /usr/local/lib/python3.12/dist-packages/transformers/processing_utils.py`	09/27/2025 6:37 AM UTC