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:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    /opt/nvidia/nvidia_entrypoint.sh
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    DYNAMO_COMMIT_SHA=c758eb5b58872fa9b2880b9ea29d058b141bb8ec
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    DYNAMO_COMMIT_SHA=c758eb5b58872fa9b2880b9ea29d058b141bb8ec
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    dynamo
    03/16/2026 9:53 PM UTC
    sha256:8e1efc6cf4c2439638335ceccccdbf14f040414c76396e3a1964fcb7ac6fb8efRUN
    RUNTIME_IMAGE_TAG=v0.5.9-cu130-runtime TARGETARCH=amd64 ENABLE_GPU_MEMORY_SERVICE=true chmod 755 /opt/dynamo/.launch_screen &&
      echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc &&
      ln -s /workspace /sgl-workspace/dynamo
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    root
    03/16/2026 9:53 PM UTC
    sha256:8d77291daaf4f30b41ac701d1a7701f9842266b845b88894a9e691ae95c60faeRUN
    RUNTIME_IMAGE_TAG=v0.5.9-cu130-runtime TARGETARCH=amd64 ENABLE_GPU_MEMORY_SERVICE=true sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen
    03/16/2026 9:53 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    SGLANG_FORCE_SHUTDOWN=1
    03/16/2026 9:53 PM UTC
    sha256:535ed4b6694e77cc7eef38447535afa9a2f89739808a52944f811c83e0e87c15COPY
    --chown=dynamo:0 --chmod=775 recipes/ /workspace/recipes/
    03/16/2026 9:53 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.