ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • 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
    sha256:e59ef01a9d4ec815087e3bf378e0185e9681cfbbbfc0b64d819a6a7410412d51COPY
    /legal /legal
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    —
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    ai.oakhaven.base=210086341041.dkr.ecr.us-west-2.amazonaws.com/ai-dynamo/oakhaven:upstream-vllm-openai-nightly-6f91edf96d3f3272945809c04702380053bff4de ai.oakhaven.dynamo.sha=5c80665ae091e470bfa1ffb2df579ed68f59fc80 ai.oakhaven.patches=/opt/oakhaven/applied-vllm.txt ai.oakhaven.model=OakHaven-Max (Qwen3_5MoeForCausalLM)
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    DYNAMO_COMMIT_SHA=5c80665ae091e470bfa1ffb2df579ed68f59fc80
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    DYNAMO_COMMIT_SHA=5c80665ae091e470bfa1ffb2df579ed68f59fc80
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    dynamo
    		08/11/2026 1:34 AM UTC
    sha256:19f15104d08c9f20074643bef745ed3c2f367df46e37556bccd3799152ff2672RUN
    RUNTIME_IMAGE=210086341041.dkr.ecr.us-west-2.amazonaws.com/ai-dynamo/oakhaven RUNTIME_IMAGE_TAG=upstream-vllm-openai-nightly-6f91edf96d3f3272945809c04702380053bff4de PYTHON_VERSION=3.12 ENABLE_KVBM=true ENABLE_GPU_MEMORY_SERVICE=true VLLM_OMNI_REF=v0.25.0rc1 NIXL_REF=v1.1.0 CUDA_MAJOR=13 MODELEXPRESS_VERSION=0.4.0 SITE_PACKAGES=/usr/local/lib/python3.12/dist-packages TARGETARCH=amd64 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
    		08/11/2026 1:34 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    root
    		08/11/2026 1:34 AM UTC
    sha256:9ce2f01678d9d65ee30a371447b6bd08c56a1f0173975c422b0b248d7c53acdaCOPY
    --chown=dynamo:0 lib /workspace/lib
    		08/11/2026 1:34 AM UTC
    sha256:88817ce86501058a5c1058fb6152be65f88430506a31dc39799817a5d074fb7bCOPY
    --chown=dynamo:0 --chmod=775 components/src/dynamo/vllm /workspace/components/src/dynamo/vllm
    		08/11/2026 1:34 AM 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.