Dynamo Tensorrt-LLM Runtime

NVIDIA

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.

Layer	Label		Created
b7592728cdafe1dfb03883980814bfc0b5003815a286088e582f73b5ecbacd4f	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	11/26/2025 5:36 PM UTC
3384cb61638770b2722017ca50af26feff92a901ec143b76bc836a9a88ad1786	ENTRYPOINT	`/opt/nvidia/nvidia_entrypoint.sh`	11/26/2025 5:36 PM UTC
c3c10bd7951f6a4508bd3563c578ff3a75c180bf5a099d03fc22ac4a8c873cdc	USER	`dynamo`	11/26/2025 5:36 PM UTC
5bb86f35135d330eec2c8e4e4815163e1f98e94a57aec467e23ea88c33406a77	RUN	`ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=f49d6873e417ef82090ed492ef00b6939bd5a8d0 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`	11/26/2025 5:36 PM UTC
dcf546e0b3dc4a1bf7535a16c642fe8301f8f3cd6282ce1273e5ccd4b26b2901	USER	`root`	11/26/2025 5:36 PM UTC
1934d05eb58de197baf0a2b14b32c5ef48a169f42de48777df1036e46426aa24	RUN	`ARCH_ALT=x86_64 ENABLE_KVBM=true PYTHON_VERSION=3.12 DYNAMO_COMMIT_SHA=f49d6873e417ef82090ed492ef00b6939bd5a8d0 sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen`	11/26/2025 5:36 PM UTC
b9463c010af7ca9b7ec1ae463029d73b76cff5abc61682fd66bd4a636aee70fe	COPY	`ATTRIBUTION* LICENSE /workspace/`	11/26/2025 5:36 PM UTC
a07119ded6f2620b7fad4dbaff8feb20a25cc13ee7b95e01ff4b6882bb446a5a	COPY	`recipes/ /workspace/recipes/`	11/26/2025 5:36 PM UTC
75a09772d82dfeebcb97a8589d3096ff5d10c5ccf64d67473a2f16e553553683	COPY	`components/ /workspace/components/`	11/26/2025 5:36 PM UTC
12b72da010dc747ce4c6c9aa210368990672f30d4ffdf394e7e2a087946e0c7e	COPY	`deploy /workspace/deploy`	11/26/2025 5:36 PM UTC