Dynamo vLLM Runtime | NVIDIA NGC

NVIDIA

Dynamo vLLM Runtime

Container

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.

Layer	Label		Created
6dd6835ac99a3d336705eecf79493ffda196df62b79ec162b767d82b511f31fd	CONFIG	`WorkingDir /workspace`	06/12/2026 7:19 AM UTC
5d5644a46d40f5c8b0661e3acd6df668da2864e8a8c6359a9160a05da7801aa7	RUN	`python3 -m pip install --force-reinstall --no-deps nvidia-cutlass-dsl-libs-cu13==4.5.2 && python3 -m pip show nvidia-cutlass-dsl-libs-cu13`	06/12/2026 7:19 AM UTC
e3afbd8abcff4e8bc4f1315bc2359b24b306ab6189d96b4500c3d1474f6e201b	USER	`root`	06/12/2026 7:19 AM UTC
f50af2769e01ad6d7c7b6bd93cf60a21e69228b50297e09cdbafaf6581841f93	ENV	`PIP_DISABLE_PIP_VERSION_CHECK=1 PIP_NO_CACHE_DIR=1`	06/12/2026 7:19 AM UTC
fbdea4fd2727f5acecf4d5cf11852a7b9a0ae8020b52f162c2cfbe1bcdf2b54c	COPY	`--chown=dynamo:0 --chmod=664 attributions-hiddentrails/vllm/amd64/ATTRIBUTIONS-Rust.txt /workspace/ATTRIBUTIONS-Rust.md`	06/12/2026 7:05 AM UTC
a8273d569af52d1474511247a1c771e226eeaa1aca2a5fed4998f4e7c1a85894	COPY	`--chown=dynamo:0 --chmod=664 attributions-hiddentrails/vllm/amd64/ATTRIBUTIONS-Python.txt /workspace/ATTRIBUTIONS-Python.md`	06/12/2026 7:05 AM UTC
fb3c8d6f46766815e72b6c1a9755d434da20e0d79f866e5f99b2e87b98061bb9	ARG	`TARGETARCH=amd64`	06/12/2026 7:05 AM UTC
bce7757a2d6ebdfc416b6f0406b4b7f6bbdb5988430012800e9fd8f755ebf2b3	ARG	`FRAMEWORK=vllm`	06/12/2026 7:05 AM UTC
e6ce83974f20f9ef52339d70880012fe3da9dd4b7bf6e12478249bd60aec8533	COPY	`--chown=dynamo:0 --chmod=664 attributions-hiddentrails/vllm/amd64/ATTRIBUTIONS-Rust.txt /workspace/ATTRIBUTIONS-Rust.md`	06/12/2026 7:05 AM UTC
5d5cf00c8475dc8e8bb25ba84ec81ce18ee9f03505939b0788dd97d5c3e0b6a1	COPY	`--chown=dynamo:0 --chmod=664 attributions-hiddentrails/vllm/amd64/ATTRIBUTIONS-Python.txt /workspace/ATTRIBUTIONS-Python.md`	06/12/2026 7:05 AM UTC