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
    08/08/2025 11:45 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    /opt/nvidia/nvidia_entrypoint.sh
    08/08/2025 11:45 PM UTC
    sha256:8c1d32752f23679768528572d68273da1f482ea1131262d14989cf3000737af1RUN
    ARCH_ALT=x86_64 TORCH_VER=2.8.0a0+5228986c39.nv25.5 TORCHVISION_VER=0.22.0a0 SETUPTOOLS_VER=78.1.1 PYTORCH_TRITON_VER=3.3.0+git96316ce52.nvinternal JINJA2_VER=3.1.6 NETWORKX_VER=3.4.2 SYMPY_VER=1.14.0 PACKAGING_VER=23.2 FLASH_ATTN_VER=2.7.3 MPMATH_VER=1.3.0 HAS_TRTLLM_CONTEXT=0 TENSORRTLLM_PIP_WHEEL=tensorrt_llm==1.0.0rc4 TENSORRTLLM_INDEX_URL=https://pypi.python.org/simple sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen &&
      echo "cat ~/.launch_screen" >> ~/.bashrc
    08/08/2025 11:45 PM UTC
    sha256:f0966edc022fca0a44cf7f9d6a95b3748a9e115ab3b0222832fa3e9834ffba5dCOPY
    ATTRIBUTION* LICENSE /workspace/
    08/08/2025 11:45 PM UTC
    sha256:4986864206e3ff9441203d04d6a61fd7f9a4612bc6c988fd28f9bf824797909bRUN
    ARCH_ALT=x86_64 TORCH_VER=2.8.0a0+5228986c39.nv25.5 TORCHVISION_VER=0.22.0a0 SETUPTOOLS_VER=78.1.1 PYTORCH_TRITON_VER=3.3.0+git96316ce52.nvinternal JINJA2_VER=3.1.6 NETWORKX_VER=3.4.2 SYMPY_VER=1.14.0 PACKAGING_VER=23.2 FLASH_ATTN_VER=2.7.3 MPMATH_VER=1.3.0 HAS_TRTLLM_CONTEXT=0 TENSORRTLLM_PIP_WHEEL=tensorrt_llm==1.0.0rc4 TENSORRTLLM_INDEX_URL=https://pypi.python.org/simple uv pip install /workspace/benchmarks
    08/08/2025 11:45 PM UTC
    sha256:286e2a0cbbd566dbc79499044b4fa146383948b5de5cae950b9f131af1332a1aCOPY
    components/backends/trtllm /workspace/components/backends/trtllm
    08/08/2025 11:45 PM UTC
    sha256:cf337d819751112fea215b345fd233d59cc4875ceaeaf3726335d46bbd5aecb2COPY
    benchmarks /workspace/benchmarks
    08/08/2025 11:45 PM UTC
    sha256:43d495fcfca7c2fe6ed22252d8120e6ac8f797a6837d71bcb3bd2de7ef9fe35eCOPY
    tests /workspace/tests
    08/08/2025 11:45 PM UTC
    sha256:e9267f209a9efb3ac8fb861914530df5d546af3b49e8b112fcaf79da453f9b49RUN
    ARCH_ALT=x86_64 TORCH_VER=2.8.0a0+5228986c39.nv25.5 TORCHVISION_VER=0.22.0a0 SETUPTOOLS_VER=78.1.1 PYTORCH_TRITON_VER=3.3.0+git96316ce52.nvinternal JINJA2_VER=3.1.6 NETWORKX_VER=3.4.2 SYMPY_VER=1.14.0 PACKAGING_VER=23.2 FLASH_ATTN_VER=2.7.3 MPMATH_VER=1.3.0 HAS_TRTLLM_CONTEXT=0 TENSORRTLLM_PIP_WHEEL=tensorrt_llm==1.0.0rc4 TENSORRTLLM_INDEX_URL=https://pypi.python.org/simple echo 'source /usr/local/bin/set_trtllm_env.sh' >> /root/.bashrc
    08/08/2025 11:45 PM UTC
    sha256:9d9766aaa4e027a0f4322f25f5f0c9c3dd64470b6b768394db49650e35e0efd6COPY
    /usr/local/bin/set_trtllm_env.sh /usr/local/bin/set_trtllm_env.sh
    08/08/2025 11:45 PM 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.