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
sglang-runtime-nightly
Container
NVIDIA
NVIDIA
sglang-runtime-nightly

The Dynamo SGLang runtime nightly 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 which is published every night.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
—
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
07/17/2026 8:47 AM UTC
sha256:80ce246b77d74f3f4f51aed970c96e9d44a508eb0532107a3525001e81c93698COPY
/legal /legal
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
—
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
DYNAMO_COMMIT_SHA=5930e58aafeed962e534f2a9da348d92a94d2fbb
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
DYNAMO_COMMIT_SHA=5930e58aafeed962e534f2a9da348d92a94d2fbb
07/17/2026 8:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
dynamo
07/17/2026 8:47 AM UTC
sha256:5b011602948f56515ebe5da592a5bc43ed63c344f96f53384f35222b5f1c784bRUN
MODELEXPRESS_VERSION=0.4.0 ENABLE_GPU_MEMORY_SERVICE=true SITE_PACKAGES="$(python3 -c 'import site; print(site.getsitepackages()[0])')" &&
  python3 -m compileall -q -j0 "$SITE_PACKAGES" &&
  (python3 -m compileall -q -j0 /sgl-workspace/sglang/python ||
  true)
07/17/2026 8:47 AM UTC
sha256:ca2a6ececced22c2754f5f2fc455df8542b72125c506b4fe9ef9e4d2bfe691a2RUN
MODELEXPRESS_VERSION=0.4.0 ENABLE_GPU_MEMORY_SERVICE=true chmod 755 /opt/dynamo/.launch_screen &&
  echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc &&
  ln -s /workspace /sgl-workspace/dynamo &&
  NSYS_BIN=$(find /opt/nvidia/nsight-compute -maxdepth 6 -type f -name nsys -executable 2>/dev/null | head -n1) &&
  if [ -n "$NSYS_BIN" ]; then ln -sf "$NSYS_BIN" /usr/local/bin/nsys; else echo "WARNING: no bundled nsys found under /opt/nvidia/nsight-compute"; fi
07/17/2026 8:47 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.