NVIDIA
NVIDIA
Dynamo Tensorrt-LLM Runtime
Container
NVIDIA
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
12/11/2025 10:32 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
12/11/2025 10:32 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
dynamo
12/11/2025 10:32 PM UTC
sha256:19aa9321c4534a1056c91e6de43e0d9e5eab99b4c1bc51b0772f1574904dadd4RUN
ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=15f1a73b375eb318ff4db7ddc89fd3d1faef0fac 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
12/11/2025 10:32 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
root
12/11/2025 10:32 PM UTC
sha256:73a7c1e630bba884602bde51f185cc4851d3010f39003650f35c1d81cd80ce34RUN
ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=15f1a73b375eb318ff4db7ddc89fd3d1faef0fac sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen
12/11/2025 10:32 PM UTC
sha256:57fc7d11002add414f6caed13cebdca9005329780c1e124c0ae633e801d2137cCOPY
ATTRIBUTION* LICENSE /workspace/
12/11/2025 10:32 PM UTC
sha256:f8fc57b46a7f0c23c744572c4e93d454f46693049dde1469a625be028867d733COPY
recipes/ /workspace/recipes/
12/11/2025 10:32 PM UTC
sha256:153483af56b1bf40dbd8e6d6fb3efd8ab1ad95c006af3208a9e77349df0fc31bCOPY
components/ /workspace/components/
12/11/2025 10:32 PM UTC
sha256:7a75646e0390a12b28f9d2eebd466f5eeca872ae209235adde4b6571b83630a7COPY
deploy /workspace/deploy
12/11/2025 10:32 PM UTC
...