Skip to main content
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
vllm-runtime-nightly
Container
NVIDIA
vllm-runtime-nightly

The Dynamo vLLM runtime nightly 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 published at a nightly cadence.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
dynamo
10/18/2026 8:34 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
EFA_VERSION=1.50.0
10/18/2026 8:34 AM UTC
sha256:4b215853530b7dbfbe2c39ae4264fa4b81034da611e7d25c32ab3784d897c07bRUN
PYTHON_VERSION=3.12 ENABLE_KVBM=true ENABLE_GPU_MEMORY_SERVICE=true VLLM_OMNI_REF=v0.31.0rc1 TRANSFORMERS_VERSION=5.14.1 TOKENIZERS_VERSION=0.22.2 NIXL_REF=v1.4.1 CUDA_MAJOR=13 MODELEXPRESS_VERSION=0.7.0 SITE_PACKAGES=/usr/local/lib/python3.12/dist-packages DYNAMO_COMMIT_SHA=3763cee6080ce6a8ab4156f055d8ce72d984458c EFA_VERSION=1.50.0 curl --retry 3 --retry-delay 2 -fsSL -o aws-efa-installer-${EFA_VERSION}.tar.gz https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_VERSION}.tar.gz &&
  tar -xf aws-efa-installer-${EFA_VERSION}.tar.gz &&
  cd aws-efa-installer &&
  apt-get update &&
  ./efa_installer.sh -y --skip-kmod --skip-limit-conf --no-verify &&
  cd .. &&
  rm -rf aws-efa-installer* &&
  ldconfig
10/18/2026 8:34 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
root
10/18/2026 8:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
EFA_VERSION=1.50.0
10/18/2026 8:33 AM UTC
sha256:15ae48a9313ac67fcff846e2c80fcb8f84204cf387c6e6657b5320198f29b31dCOPY
/legal /legal
10/18/2026 8:33 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1RUN
PYTHON_VERSION=3.12 ENABLE_KVBM=true ENABLE_GPU_MEMORY_SERVICE=true VLLM_OMNI_REF=v0.31.0rc1 TRANSFORMERS_VERSION=5.14.1 TOKENIZERS_VERSION=0.22.2 NIXL_REF=v1.4.1 CUDA_MAJOR=13 MODELEXPRESS_VERSION=0.7.0 SITE_PACKAGES=/usr/local/lib/python3.12/dist-packages DYNAMO_COMMIT_SHA=3763cee6080ce6a8ab4156f055d8ce72d984458c python3 -c 'import dynamo.artifacts.vllm.capture; import dynamo.artifacts.runtime'
10/18/2026 8:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
—
10/18/2026 8:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
DYNAMO_COMMIT_SHA=3763cee6080ce6a8ab4156f055d8ce72d984458c
10/18/2026 8:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
DYNAMO_COMMIT_SHA=3763cee6080ce6a8ab4156f055d8ce72d984458c
10/18/2026 8:33 AM UTC
1-10 of 178 items

Modal Content

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.

Manage Settings