ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
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
49499ffc21b36b65a8e7ea1349a22ef463424da106ac0590b46ec8b37839fdffCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
08/08/2025 11:45 PM UTC
a1696b094d06d50f235525287b6bb36585519b5ef0ca78b9b53a9c0de71fdec6ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
08/08/2025 11:45 PM UTC
614bbfb9ddcbc377297a7cf9ba49809554ae1688de3e3d3878c261229622d069RUN
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
744438f2e10d0fbf5194b69476be12a6e7907a3e5f8d6940d690f7aa62e48176COPY
ATTRIBUTION* LICENSE /workspace/
08/08/2025 11:45 PM UTC
50ea5cdf8670aaac8bee08b5276c0bd8bbf479d0c42be520d7be65175e9ed0d6RUN
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
4ea0ece95847f87afad4ec0b3377589c93b007abc3431487f38b569e7bc748daCOPY
components/backends/trtllm /workspace/components/backends/trtllm
08/08/2025 11:45 PM UTC
d7d0c415629f3c8ddcad3d035e39df0d08ae5d8824cd7bdb76744b114a3a9a6bCOPY
benchmarks /workspace/benchmarks
08/08/2025 11:45 PM UTC
7525e2a236d5453ed794a8a383df555539aac4d3e882b51cafc61ced9ab3448aCOPY
tests /workspace/tests
08/08/2025 11:45 PM UTC
90eebd45922e7710fee5da46d6176e7814038202235063fbc318f4bdb9a08f65RUN
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
016fd5597d798a6620a6e6333aab6405e9fe3aedf181567b1b02f87bd555d874COPY
/usr/local/bin/set_trtllm_env.sh /usr/local/bin/set_trtllm_env.sh
08/08/2025 11:45 PM UTC
...