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
a45e44fb5761045fa4a986326ab82d6cc4e210f2888af05e65a10b660e497c04CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
11/07/2025 1:36 AM UTC
f5927f4dd1a44e857e9ba40647cfc1f05d582f525526ff1b725567c454657a91ENTRYPOINT
/opt/nvidia/nvidia_entrypoint.sh
11/07/2025 1:36 AM UTC
88517032fe00b19d416a866e02716746e953d2abd52865570d484881c078d236COPY
components/ /workspace/components/
11/07/2025 1:36 AM UTC
e38331ba4481acfb5b815044811615ded7b9c80ea7e6107da8b5515454b7a65dCOPY
deploy /workspace/deploy
11/07/2025 1:36 AM UTC
380ff04851bd2b101bc3a709c64064397cb6b076f640230c423ce3f6a3fc303cCOPY
benchmarks /workspace/benchmarks
11/07/2025 1:36 AM UTC
12ae8e95745dfeb4221161027e4c1d27648c6383f9c07d19e28d878bbbb29340COPY
examples /workspace/examples
11/07/2025 1:36 AM UTC
7515f40408288b37e2fd94195c6600bd9c8987710fea2c634595351be95dfee8COPY
tests /workspace/tests
11/07/2025 1:36 AM UTC
7e49df1b38a0aaea2d69384e847d5e176de95b255eec1fd58bd366a1d1eacce7RUN
BUILD_TYPE=all DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee DEEPEP_GB_COMMIT=1b14ad661c7640137fcfe93cccb2694ede1220b0 CMAKE_BUILD_PARALLEL_LEVEL=2 FLASHMLA_COMMIT=1408756a88e52a25196b759eaf8db89d2b51b5a1 SGL_KERNEL_VERSION=0.3.15 SGLANG_COMMIT=0.5.3.post2 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 sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen &&
  echo "cat ~/.launch_screen" >> ~/.bashrc
11/07/2025 1:36 AM UTC
e94ab3f6bdaecf9ab50833a9d1b7269cf9223cea6df1eeb14bf8e0190f391064COPY
container/launch_message.txt /workspace/launch_message.txt
11/07/2025 1:36 AM UTC
35882a16f71520fca81f013d82d38cbe92cfed3dea6cc9a569b4cc672590e2e2COPY
ATTRIBUTION* LICENSE /workspace/
11/07/2025 1:36 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.