ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • NVIDIA
    NVIDIA
    Dynamo SGLang Runtime
    Container
    NVIDIA
    NVIDIA
    Dynamo SGLang Runtime

    The Dynamo SGLang runtime image is a containerized build of Dynamo + SGLang which serves as the base runtime environment for sglang based inference with Dynamo's distributed inference framework.

  • LayerLabelCreated
    sha256:0653755905227111a2ebcc23178c5e171aac1c673b0dc8d553af96602ec4c8c2COPY
    ATTRIBUTIONS-Python.md ATTRIBUTIONS-Rust.md ATTRIBUTIONS.md /workspace/
    		04/30/2026 10:30 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
    bash
    		04/30/2026 7:57 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    —
    		04/30/2026 7:57 PM UTC
    sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
    /workspace
    		04/30/2026 7:57 PM UTC
    sha256:05e90fef89ca6b4becc2ea2e10071866cdc8ea78cd6e0b1fd7e72026b8778c60RUN
    apt-get purge -y libx264-164 libx265-199 libde265-0 libavcodec60 libxvidcore4 &&
  rm -rf /var/lib/apt/lists/*
    		04/30/2026 7:57 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    SGLANG_JIT_DEEPGEMM_PRECOMPILE=0 SGLANG_JIT_DEEPGEMM_FAST_WARMUP=1
    		04/29/2026 4:40 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    PYTHONPATH=/workspace/sglang/python:/workspace/components/src
    		04/29/2026 4:40 AM UTC
    sha256:9ee43980301dfd95323c91aaf8759252c8ceb5fcf253a5a3b9885e9a9deb83aeCOPY
    /workspace/components/src/dynamo /workspace/components/src/dynamo
    		04/29/2026 4:40 AM UTC
    sha256:d1a3a240e86781a4db401001ea92f76fb1a214f59a425211d9989b5ea5138b09RUN
    pip install --no-cache-dir --force-reinstall --no-deps /opt/dynamo/wheelhouse/ai_dynamo_runtime*.whl /opt/dynamo/wheelhouse/ai_dynamo-*.whl &&
  python3 -c "from dynamo._core import get_tool_parser_names; assert 'deepseek_v4' in get_tool_parser_names(), 'V4 parser missing!'; print('V4 parser verified')"
    		04/29/2026 4:40 AM UTC
    sha256:1c1e0ac5318ce0a3b067605f87aaa08f143652bf7b0c77857e915f2a41619355COPY
    /opt/dynamo/wheelhouse /opt/dynamo/wheelhouse
    		04/29/2026 4:40 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.