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
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/sgl-workspace/dynamo/components/backends/sglang
09/10/2025 9:58 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
SGL_FORCE_SHUTDOWN=1
09/10/2025 9:58 PM UTC
sha256:28b5a3826fb837ebff91a51b0c51d30793205964656ac3dafc4e13f26e98d2deRUN
SGLANG_COMMIT=ff1f68252c2b5b343aa6ef2aa14e6d4753ae4871 BUILD_TYPE=blackwell DEEPEP_COMMIT=1b14ad661c7640137fcfe93cccb2694ede1220b0 CMAKE_BUILD_PARALLEL_LEVEL=2 SGL_KERNEL_VERSION=0.3.4 MODE=hopper ARCH=amd64 ARCH_ALT=x86_64 NIXL_UCX_REF=v1.19.0 NIXL_TAG=0.5.0 CMAKE_VERSION=3.31.8 RUST_VERSION=1.89.0 CARGO_BUILD_JOBS=16 cd dynamo/lib/bindings/python &&
  pip install --break-system-packages -e . &&
  cd /sgl-workspace/dynamo &&
  pip install --break-system-packages .
09/10/2025 9:58 PM UTC
sha256:db0d8b7eb7fedad49c9673a71c213e738e0f7e038cf5735f68e9e71694a07f89RUN
SGLANG_COMMIT=ff1f68252c2b5b343aa6ef2aa14e6d4753ae4871 BUILD_TYPE=blackwell DEEPEP_COMMIT=1b14ad661c7640137fcfe93cccb2694ede1220b0 CMAKE_BUILD_PARALLEL_LEVEL=2 SGL_KERNEL_VERSION=0.3.4 MODE=hopper ARCH=amd64 ARCH_ALT=x86_64 NIXL_UCX_REF=v1.19.0 NIXL_TAG=0.5.0 CMAKE_VERSION=3.31.8 RUST_VERSION=1.89.0 CARGO_BUILD_JOBS=16 cd dynamo &&
  cargo build --release
09/10/2025 9:57 PM UTC
sha256:4cd9bde3d0d26db6abef7577d19a44e80448ffee433d2462030ae837e080830dCOPY
. ./dynamo
09/10/2025 9:47 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
CARGO_BUILD_JOBS=16
09/10/2025 4:57 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
CARGO_BUILD_JOBS
09/10/2025 4:57 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
PATH=/usr/local/bin/etcd:/usr/local/cargo/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
09/10/2025 4:57 PM UTC
sha256:e08ede5994b663407a9de400c12882b5b669b3275406b1f8afa792117a9a9041RUN
SGLANG_COMMIT=ff1f68252c2b5b343aa6ef2aa14e6d4753ae4871 BUILD_TYPE=blackwell DEEPEP_COMMIT=1b14ad661c7640137fcfe93cccb2694ede1220b0 CMAKE_BUILD_PARALLEL_LEVEL=2 SGL_KERNEL_VERSION=0.3.4 MODE=hopper ARCH=amd64 ARCH_ALT=x86_64 NIXL_UCX_REF=v1.19.0 NIXL_TAG=0.5.0 CMAKE_VERSION=3.31.8 RUST_VERSION=1.89.0 CARGO_BUILD_JOBS=16 wget --tries=3 --waitretry=5 https://github.com/etcd-io/etcd/releases/download/${ETCD_VERSION}/etcd-${ETCD_VERSION}-linux-arm64.tar.gz -O /tmp/etcd.tar.gz &&
  mkdir -p /usr/local/bin/etcd &&
  tar -xzf /tmp/etcd.tar.gz -C /usr/local/bin/etcd --strip-components=1 &&
  rm /tmp/etcd.tar.gz
09/10/2025 4:57 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
ETCD_VERSION=v3.5.21
09/10/2025 4:57 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.