Dynamo vLLM Runtime | NVIDIA NGC

NVIDIA

Dynamo vLLM Runtime

Container

NVIDIA

Dynamo vLLM Runtime

The Dynamo vLLM runtime image is a containerized build of Dynamo + vLLM which serves as the base runtime environment for vLLM based inference with Dynamo's distributed inference framework.

Layer	Label		Created
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	CMD	`—`	12/13/2025 12:07 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/opt/nvidia/nvidia_entrypoint.sh`	12/13/2025 12:07 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	USER	`dynamo`	12/13/2025 12:07 AM UTC
sha256:ab4058e93584861405818e63dbe528ddb95b55c4c6548209ead772874d9faf36	RUN	`ARCH_ALT=x86_64 PYTHON_VERSION=3.12 ENABLE_KVBM=true DYNAMO_COMMIT_SHA=4e4b487ba2baa3f8887dfa49cf6cb35c7bb62022 chmod 755 /opt/dynamo/.launch_screen && echo 'source /opt/dynamo/venv/bin/activate' >> /etc/bash.bashrc && echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc`	12/13/2025 12:07 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	USER	`root`	12/13/2025 12:07 AM UTC
sha256:a2c022dd3a062b2dade824913370a1fde4b39a88d75932d5b52d40aa4c27c824	RUN	`ARCH_ALT=x86_64 PYTHON_VERSION=3.12 ENABLE_KVBM=true DYNAMO_COMMIT_SHA=4e4b487ba2baa3f8887dfa49cf6cb35c7bb62022 sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen`	12/13/2025 12:07 AM UTC
sha256:fafd7ff41f1e30395d92a86b7354fb9f944cbb8ad6c00dcb2a16c2ac4cafc5cb	COPY	`--chown=dynamo: ATTRIBUTION* LICENSE /workspace/`	12/13/2025 12:07 AM UTC
sha256:b6736a09c3286f68c718a7f37a4ad5e2aa85fa54d02122561a7bdbdc06421a79	COPY	`--chown=dynamo: lib/ /workspace/lib/`	12/13/2025 12:07 AM UTC
sha256:04e4ce85a60378312ad849778f5c82c013d2d3a54fc9028ad50794227fb6ab32	COPY	`--chown=dynamo: components/ /workspace/components/`	12/13/2025 12:07 AM UTC
sha256:13c3ba6bbba6e2ff0c36d6844a2b324a4a6346308022ab3517372afc0689aaf5	COPY	`--chown=dynamo: recipes/ /workspace/recipes/`	12/13/2025 12:07 AM UTC