NVIDIA
NVIDIA
Dynamo SGLang Runtime
Container
NVIDIA
NVIDIA
Dynamo SGLang Runtime

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

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    DYNAMO_COMMIT_SHA=115531a0c0bf58ff12df7ef7e69082d50fd4d707
    01/15/2026 2:06 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    DYNAMO_COMMIT_SHA=115531a0c0bf58ff12df7ef7e69082d50fd4d707
    01/15/2026 2:06 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    dynamo
    01/15/2026 2:06 PM UTC
    sha256:82819f47334f75a68e3b4a496977fe341841809a580264ed76003a57a414972dRUN
    RUNTIME_IMAGE_TAG=v0.5.6.post2-cu130-runtime chmod 755 /opt/dynamo/.launch_screen &&
      echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc &&
      ln -s /workspace /sgl-workspace/dynamo
    01/15/2026 2:06 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    root
    01/15/2026 2:06 PM UTC
    sha256:784a4a4eff752226aef0414d0972d446945ef34800df8d93d0012c7b0ea7db71RUN
    RUNTIME_IMAGE_TAG=v0.5.6.post2-cu130-runtime sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen
    01/15/2026 2:06 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    SGLANG_FORCE_SHUTDOWN=1
    01/15/2026 2:06 PM UTC
    sha256:0140db8552b8e55ae505ce4105e4efbefb4389b07c27546ce5ca6803a9d54f89COPY
    --chown=dynamo:0 --chmod=775 recipes/ /workspace/recipes/
    01/15/2026 2:06 PM UTC
    sha256:ada70ab2a0f240e51e53110b8435b8b1b5418075cd5a99888a439d3bf9ccfd53COPY
    --chown=dynamo:0 --chmod=775 components/ /workspace/components/
    01/15/2026 2:06 PM UTC
    sha256:1ec80e7f97b0567203328e2a79625fc513e474ae0d36a4628d407e8333c7174aCOPY
    --chown=dynamo:0 --chmod=775 deploy /workspace/deploy
    01/15/2026 2:06 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.