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
d1dd350322052885655d4716893642962d6ec1bd3121e803fa8221f44a869024CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
08/27/2025 3:33 AM UTC
36d765ca03823abd33a6112ab181c9b9f8cb370005f01f7c37d069c2c404e270ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
08/27/2025 3:33 AM UTC
2871be492fa21f242300bf885fb88015aa779a14a4a5d32f6ea6ab4ae190fd51RUN
ARCH_ALT=x86_64 TORCH_VER=2.8.0a0+5228986c39.nv25.6 TORCHVISION_VER=0.22.0a0+95f10a4e SETUPTOOLS_VER=78.1.1 PYTORCH_TRITON_VER=3.3.0+git96316ce52.nvinternal JINJA2_VER=3.1.6 NETWORKX_VER=3.5 SYMPY_VER=1.14.0 PACKAGING_VER=23.2 FLASH_ATTN_VER=2.7.4.post1 MPMATH_VER=1.3.0 HAS_TRTLLM_CONTEXT=0 TENSORRTLLM_PIP_WHEEL=tensorrt_llm==1.0.0rc6 TENSORRTLLM_INDEX_URL=https://pypi.python.org/simple sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen &&
  echo "cat ~/.launch_screen" >> ~/.bashrc
08/27/2025 3:33 AM UTC
a74b85989813360551f0486c5cc44be1b5cdee05ba75d4064634cb6d12571dbbCOPY
ATTRIBUTION* LICENSE /workspace/
08/27/2025 3:33 AM UTC
7c656a904d5c86d66f0eb57accaa62073ae1f5ca23922e59abfd121aabf6603bRUN
ARCH_ALT=x86_64 TORCH_VER=2.8.0a0+5228986c39.nv25.6 TORCHVISION_VER=0.22.0a0+95f10a4e SETUPTOOLS_VER=78.1.1 PYTORCH_TRITON_VER=3.3.0+git96316ce52.nvinternal JINJA2_VER=3.1.6 NETWORKX_VER=3.5 SYMPY_VER=1.14.0 PACKAGING_VER=23.2 FLASH_ATTN_VER=2.7.4.post1 MPMATH_VER=1.3.0 HAS_TRTLLM_CONTEXT=0 TENSORRTLLM_PIP_WHEEL=tensorrt_llm==1.0.0rc6 TENSORRTLLM_INDEX_URL=https://pypi.python.org/simple python3 -m pip install --no-cache-dir --break-system-packages /workspace/benchmarks
08/27/2025 3:33 AM UTC
69684f6c4015b9e4ec313ec38170737034a9058071b9175bdcc42300db3db7acCOPY
components/backends/trtllm /workspace/components/backends/trtllm
08/27/2025 3:33 AM UTC
9c857c01a7cb0c99b51debc46dd2d9b6f217eac2648f16c3e9337b74354413efCOPY
benchmarks /workspace/benchmarks
08/27/2025 3:33 AM UTC
0205842aac1df0144a4048b0347f33bb7a8ccb1c7e79903e9bece39bf282e2b7COPY
tests /workspace/tests
08/27/2025 3:33 AM UTC
f350ed8fd8e94f855e7bd2b550c384b1231efc9abc3c78788925f9652188df4eCOPY
/usr/local/lib/python3.12/dist-packages/pytorch_triton-3.3.0+git96316ce52.nvinternal.dist-info /usr/local/lib/python3.12/dist-packages/pytorch_triton-3.3.0+git96316ce52.nvinternal.dist-info
08/27/2025 3:33 AM UTC
1996a92cbd0766ef7c0deb6f07f5acc687a194617c9bdcddbd6e32d04737f0f6COPY
/usr/local/lib/python3.12/dist-packages/triton /usr/local/lib/python3.12/dist-packages/triton
08/27/2025 3:33 AM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.