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 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
477026b4c612e2e88e1a4dfb99f2fed0ba1b7df304e37cdb1990496bc13fae84CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
11/26/2025 5:37 PM UTC
e3ff6a8111e1e99ed0c439c271a436a9472cdec7ac2b1caeb60c909a5011b7b2ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
11/26/2025 5:37 PM UTC
fcab433ee5633ff3d888953116937134612cdc9c3810f872f3f11ff445a31297COPY
--chown=dynamo: recipes/ /workspace/recipes/
11/26/2025 5:37 PM UTC
171768a1c1ddfeb83a776b96ebfa5240739b5c5a4a094e97023e5b56e39bc8ecCOPY
--chown=dynamo: components/ /workspace/components/
11/26/2025 5:37 PM UTC
6f321d5de9912632d132d9f891d6b8b29d3a866809b337c12ed4048d9bb10240COPY
--chown=dynamo: deploy /workspace/deploy
11/26/2025 5:37 PM UTC
2cb9c0a770287f12a4207a17a0316f4085a9b51346f7cf86e37b2707f16df3f7COPY
--chown=dynamo: benchmarks /workspace/benchmarks
11/26/2025 5:37 PM UTC
5552826dc7409ac605fedb721e9ab2b3d1b817bdb4ae4192101f22c30088414cCOPY
--chown=dynamo: examples /workspace/examples
11/26/2025 5:37 PM UTC
d3ac744d80fb88b74a08811eab92570885dea827fe46817e52a234ad04451a85COPY
--chown=dynamo: tests /workspace/tests
11/26/2025 5:37 PM UTC
24c17243c96942dc26df35c6a15bcb7f1d7ab982f12e563faee4466bb2e1b4adUSER
dynamo
11/26/2025 5:37 PM UTC
a1afccf5c3e748d7cda14e4268474337df259fb19a633cbe6b09939da4225acbRUN
BUILD_TYPE=all DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee DEEPEP_GB_COMMIT=1b14ad661c7640137fcfe93cccb2694ede1220b0 CMAKE_BUILD_PARALLEL_LEVEL=2 SGL_KERNEL_VERSION=0.3.16.post5 SGLANG_COMMIT=0.5.4.post3 GDRCOPY_COMMIT=v2.4.4 NVSHMEM_VERSION=3.3.9 GRACE_BLACKWELL=false ARCH=amd64 ARCH_ALT=x86_64 PYTHON_VERSION=3.10 USE_SCCACHE=true SCCACHE_BUCKET=ai-dynamo-sccache SCCACHE_REGION=us-west-2 CARGO_BUILD_JOBS=16 CUDA_VERSION=12.9.1 ARCH=amd64 ARCH_ALT=x86_64 PYTHON_VERSION=3.10 DYNAMO_COMMIT_SHA=f49d6873e417ef82090ed492ef00b6939bd5a8d0 chmod 755 /opt/dynamo/.launch_screen &&
  echo 'source /opt/dynamo/venv/bin/activate' >> /etc/bash.bashrc &&
  echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc
11/26/2025 5:37 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.