NVIDIA
NVIDIA
Dynamo vLLM Runtime
Container
NVIDIA
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.

LayerLabelCreated
6dc8f20fcfccdce903f6aefad757bde80c56d33e298e6ae8110b7a65e85d2bdfCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
01/13/2026 11:20 PM UTC
a867bcafb4ba7031e85b089bd6486843746c60951db1e1fb846d0e38563667d2ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
01/13/2026 11:20 PM UTC
0744768e55e6d0495eb306377390745f77da80b3a69dd79b82f830f806f5c3b9ENV
DYNAMO_COMMIT_SHA=661467c6d3d5aff1048f210a0142f73b825f3310
01/13/2026 11:20 PM UTC
04963dabc0c3471e691579b3f746470ed7834450c2aa8e61de4bfd3b24b24164ARG
DYNAMO_COMMIT_SHA=661467c6d3d5aff1048f210a0142f73b825f3310
01/13/2026 11:20 PM UTC
984dd69a1c2d2749c32095575ad8ee7578c9b7004afb521a2635f24c0d4cfb3bUSER
dynamo
01/13/2026 11:20 PM UTC
a7b56088aaa1096dc1e8e6f5c00aae9316e39ec7c81aa3fb78d823e09bd63a68RUN
ARCH_ALT=x86_64 PYTHON_VERSION=3.12 ENABLE_KVBM=true /bin/bash -l -o pipefail -c chmod g+w /workspace /workspace/* /opt/dynamo /opt/dynamo/* ${VIRTUAL_ENV} &&
  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
01/13/2026 11:20 PM UTC
c002380fa25449b8693ed11141abc412ff0c6508a1706a72bae10007dca1f3d0USER
root
01/13/2026 11:20 PM UTC
ab0fe6c3db67aac96f72396219f36cb85bbc83a367c7226e2b96f3b6421e8b13RUN
ARCH_ALT=x86_64 PYTHON_VERSION=3.12 ENABLE_KVBM=true /bin/bash -l -o pipefail -c sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen
01/13/2026 11:20 PM UTC
f017611ef84f316fd7b8c150430b87d0bb225a5591bee609e72eecde9a0a1a58COPY
--chown=dynamo:0 --chmod=775 lib/ /workspace/lib/
01/13/2026 11:20 PM UTC
4765a70414dc7b65478e843af826c072cd5c982da3b13159d14b3ed8c3223f2aCOPY
--chown=dynamo:0 --chmod=775 components/ /workspace/components/
01/13/2026 11:20 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.