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
19662df764a3d8fb16ed58e7ecea9ae83bcc14c3abc4bcf215d8cda59d3bcd9d	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace; ExposedPorts 6006/tcp, 8888/tcp`	10/23/2025 3:26 AM UTC
c170210e0d45833f65715fb59400258a6d64aeed4025d020228c0fa483f19ff6	ARG	`NVIDIA_BUILD_REF=13aa3ebd28c5236ad70c845a1c4ef7be5175729d`	10/23/2025 3:26 AM UTC
9250c2a26410e2ca8521b4f9d38bb92c3a0c0aac390a9ff01b41dd0716922f6e	LABEL	`com.nvidia.build.id=224204847`	10/23/2025 3:26 AM UTC
e5c189f76602d83a0c87cee73faa2ce01819f9d53c741f57af6ec9951bc15cdc	ENV	`NVIDIA_BUILD_ID=224204847`	10/23/2025 3:26 AM UTC
855582c1324b83342a017e07751ec3df2dcfc1da8572a1893c1e9a3397a0f91f	ARG	`NVIDIA_BUILD_ID=224204847`	10/23/2025 3:26 AM UTC
4b3742df8a594a0c196c6a725c02a48ab27e5f1df7e3213dbed6705ef39379e2	ENV	`NVIDIA_VLLM_VERSION=25.10`	10/23/2025 3:26 AM UTC
19627269b2a430a66ec94f571b0214471270a39a988e6c766da9b0514e11842c	ARG	`NVIDIA_VLLM_VERSION=25.10`	10/23/2025 3:26 AM UTC
1317e62e867ca0c705bef449eef91533580daf4d15a51e8aba9e659614c4cad2	LABEL	`com.nvidia.vllm.version=0.10.2+9dd9ca32`	10/23/2025 3:26 AM UTC
1e7e6eec4f10f3c223e3f08059750bc8882925b682e12854521c9893bda89adf	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	10/23/2025 3:26 AM UTC
5fccb996583bab3c4295ff34d41ceac3fcb05555f0a300d2cfbffab01d0464ed	RUN	`TARGETARCH=amd64 VLLM_VERSION=0.10.2+9dd9ca32 sed -i -E 's/^([[:space:]]*)from \.modeling_utils import PreTrainedAudioTokenizerBase/\1pass/' /usr/local/lib/python3.12/dist-packages/transformers/processing_utils.py`	10/23/2025 3:26 AM UTC