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
Triton Inference Server
Container
NVIDIA
NVIDIA
Triton Inference Server

Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

NVIDIA AI Enterprise Supported
LayerLabelCreated
960bd5748af45b486dc1ae9c80ebcc2b6e8777ae65fddecdd4e4f10b213ba227CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
08/22/2025 1:18 AM UTC
974da07cc85a39a4301f6e4a2b0f1af4076b7d35b7169597e229bc7c098528a7ENV
LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
08/22/2025 1:18 AM UTC
86821daeb8d975b9bbf4e779aec4468fb44394e7d97a82ba9ef61a4a27ab51cfENV
LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
08/22/2025 1:18 AM UTC
155c9200dbd111ecf47bee6b3add85603198f2eb4f8d9b838459c5acaf87541bENV
PATH=/workspace/install/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin
08/22/2025 1:18 AM UTC
ab95d94e31727b0fcdec0290392aee305f0c1c0693bd52a6207cc0f9489a038eENV
NVIDIA_BUILD_ID=202022692
08/22/2025 1:18 AM UTC
e4f196c7eb6df70646a065d7ffd3ad7d309c1f3e473b0b6aec5333184c809f48ENV
NVIDIA_TRITON_SERVER_SDK_VERSION=25.08
08/22/2025 1:18 AM UTC
3f821909dc8783f19300f5c8b7bdc28919bfaa187e0e61283c90e38229f61fa0ARG
NVIDIA_BUILD_ID=202022692
08/22/2025 1:18 AM UTC
f7d02c4b1778c9d1114a4be013bdac695bd4aae2b9ef10140c2c653525034939ARG
NVIDIA_TRITON_SERVER_SDK_VERSION=25.08
08/22/2025 1:18 AM UTC
92bcdae0c811b9a78e16a75a4466d10a3d2dddeabd9a9e79aa678c1d712f5028RUN
DCGM_VERSION=4.4.0-1 TRITON_REPO_ORGANIZATION=https://github.com/triton-inference-server TRITON_CORE_REPO_TAG=r25.08 TARGETPLATFORM=linux/arm64 TRITON_ENABLE_GPU=ON sed 's/Server/Server SDK/' /opt/nvidia/entrypoint.d/10-banner.txt | sed 's/^===/=======/' > /opt/nvidia/entrypoint.d/10-banner.new &&
  mv /opt/nvidia/entrypoint.d/10-banner.new /opt/nvidia/entrypoint.d/10-banner.txt
08/22/2025 1:18 AM UTC
fa387982bf0d9047c6da348abd0dcc20e0169f5922799ab8cb5bc13568219110COPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
08/22/2025 1:18 AM UTC
...