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:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
05/02/2026 1:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
05/02/2026 1:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
dynamo
05/02/2026 1:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
EFA_VERSION=1.47.0
05/02/2026 1:30 AM UTC
sha256:74d64b2c3c4db737602ca2f15ab2915f1f4c70e6b4359e5e08fa55382a7f0729RUN
DEVICE=cuda PYTHON_VERSION=3.12 SITE_PACKAGES=/opt/dynamo/venv/lib/python3.12/site-packages ENABLE_KVBM=true ENABLE_GPU_MEMORY_SERVICE=true ENABLE_MODELEXPRESS_P2P=false MODELEXPRESS_REF=76fc5d7f06c37121ee8789a29fac6f9b08c4743a DYNAMO_COMMIT_SHA=368c9f5f2985f1cddc8de490315bc30d46e23c8a EFA_VERSION=1.47.0 /bin/bash -l -o pipefail -c mkdir -p /tmp/efa &&
  cd /tmp/efa &&
  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 &&
  rm -rf /tmp/efa &&
  rm -rf /opt/amazon/aws-ofi-nccl &&
  ldconfig
05/02/2026 1:30 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
root
05/02/2026 1:01 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
EFA_VERSION=1.47.0
05/02/2026 1:01 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
05/02/2026 1:01 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
05/02/2026 1:01 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
VLLM_USE_FLASHINFER_SAMPLER=1
05/02/2026 1:01 AM UTC
...