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
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
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
TCMALLOC_RELEASE_RATE=200
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
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
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_BUILD_ID=193148868
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_TRITON_SERVER_SDK_VERSION=25.07
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
NVIDIA_BUILD_ID=193148868
07/28/2025 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
NVIDIA_TRITON_SERVER_SDK_VERSION=25.07
07/28/2025 4:10 PM UTC
sha256:d7574c382276e386d93b230b62bbf425c3f32d6771f6a02d3784581eab71e8c7RUN
DCGM_VERSION=3.3.6 TRITON_REPO_ORGANIZATION=https://github.com/triton-inference-server TRITON_CORE_REPO_TAG=r25.07 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
07/28/2025 4:10 PM UTC
sha256:a5f2509994cf7fd375d1dbf2712af07ff9752006141a1e37de94a7de0d98bdccCOPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
07/28/2025 4:10 PM UTC
...