Skip to main content
NVIDIA
Dynamo vLLM Runtime (Enterprise)
Container
NVIDIA
Dynamo vLLM Runtime (Enterprise)

Containerized build of the Dynamo runtime for vLLM. Eligible for NVIDIA Enterprise Support. No functional or binary differences from its corresponding OSS artifact.

LayerLabelCreated
sha256:66619c105db94703ad70b719e7f59efdb06565cb4e04e43294c5e272291b21deCOPY
/legal /legal
08/27/2026 10:03 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
08/27/2026 10:03 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
DYNAMO_COMMIT_SHA=2ecbdfdf192c69c02c6d21e931d20d3b4a0bb64a
08/27/2026 10:03 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
DYNAMO_COMMIT_SHA=2ecbdfdf192c69c02c6d21e931d20d3b4a0bb64a
08/27/2026 10:03 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
dynamo
08/27/2026 10:03 PM UTC
sha256:72bdb593d642eadcbb5821c009492595972043f1ba0e53649a6739408e86a26eRUN
PYTHON_VERSION=3.12 ENABLE_KVBM=true ENABLE_GPU_MEMORY_SERVICE=true VLLM_OMNI_REF=v0.26.0rc1 NIXL_REF=v1.3.2 CUDA_MAJOR=13 MODELEXPRESS_VERSION=0.5.0 SITE_PACKAGES=/usr/local/lib/python3.12/dist-packages sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen &&
  chmod 755 /opt/dynamo/.launch_screen &&
  echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc
08/27/2026 10:03 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
root
08/27/2026 10:03 PM UTC
sha256:8cf138992d6099371466c455f12131ed8eb2c26b236e35d67dd3f087349eb1d7COPY
--chown=dynamo:0 lib /workspace/lib
08/27/2026 10:03 PM UTC
sha256:897ec264a5788c9307b1eee940002e64870ea03b691b3153c78a05d16288ae3fCOPY
--chown=dynamo:0 --chmod=775 components/src/dynamo/vllm /workspace/components/src/dynamo/vllm
08/27/2026 10:03 PM UTC
sha256:c565cfc955e63de4e3d125d9d16e5bcc1d0b73b24ea3585e0e209cd5d0c065edCOPY
--chown=dynamo:0 --chmod=775 components/src/dynamo/frontend /workspace/components/src/dynamo/frontend
08/27/2026 10:03 PM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.