Skip to main content
NVIDIA
Dynamo Tensorrt-LLM Runtime
Container
NVIDIA
Dynamo Tensorrt-LLM Runtime

The Dynamo TensorRT-LLM runtime image is a containerized build of Dynamo + TensorRT-LLM which serves as the base runtime environment for tensorrt-llm based inference with Dynamo's distributed inference framework.

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
    12/05/2025 8:01 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    /opt/nvidia/nvidia_entrypoint.sh
    12/05/2025 8:01 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    dynamo
    12/05/2025 8:01 PM UTC
    sha256:0587d3e7f725617cf68ee29595162d4062927679200a4e806807ea6d16e14e8bRUN
    ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=41a72ab36698ce3eba0fba9af1dfad124d9e71ea chmod 755 /opt/dynamo/.launch_screen &&
      echo 'source /opt/dynamo/venv/bin/activate' >> /etc/bash.bashrc &&
      echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc
    12/05/2025 8:01 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
    root
    12/05/2025 8:01 PM UTC
    sha256:728f90d184befbe48ce70623883c889981b5d85f3fde3cc979e638b0da7df951RUN
    ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=41a72ab36698ce3eba0fba9af1dfad124d9e71ea sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen
    12/05/2025 8:01 PM UTC
    sha256:f482e08dda14532b2db649afffee39c0f49955170128ef47f8f3eb5f8fc53598COPY
    ATTRIBUTION* LICENSE /workspace/
    12/05/2025 8:01 PM UTC
    sha256:ce98a88724c666cb97a0c67939d859eb3aa0196cb0d284e42b6bfbaabca8be30COPY
    recipes/ /workspace/recipes/
    12/05/2025 8:01 PM UTC
    sha256:8da475e9b9d237c6ba5c546c7bf0a6b045d079b755473c17184d4a3eaf6f75c4COPY
    components/ /workspace/components/
    12/05/2025 8:01 PM UTC
    sha256:798e4c81239b71926cd579262ba3130427c261e5404a9dc7ec038220e2a9a637COPY
    deploy /workspace/deploy
    12/05/2025 8:01 PM UTC
    ...