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
9c03f88b24e5391c9f12bc85a2945dd3f6ec9996dce053219609f1b237977f2dCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
11/20/2025 9:53 PM UTC
2c4442607811ea23e14e87fcf274ad4b04de46e9f39e162a4c6ea22e8a4e1279LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
11/20/2025 9:53 PM UTC
ab7d91ae9e2489339fdaf4abc3b70d442df6d23121179f8f6f2688861ccaf6a0RUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 chown triton-server:triton-server /opt/tritonserver/caches
11/20/2025 9:53 PM UTC
38a0586e61d9aa020d0764d4a099e3e11df2f1120e308b1ed7657e2cf8a90c4bCOPY
--chown=1000:1000 /opt/tritonserver/caches/local /opt/tritonserver/caches/local
11/20/2025 9:53 PM UTC
2cd50bc964954f70cca9360ff8e7cf7b8a4bc2188981914ed7a375d2a3b58433RUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 chown triton-server:triton-server /opt/tritonserver/repoagents
11/20/2025 9:53 PM UTC
4ef2a27658646c88b35317570b0210cb55807ea5af6e568946427cb9a62ff636COPY
--chown=1000:1000 /opt/tritonserver/repoagents/checksum /opt/tritonserver/repoagents/checksum
11/20/2025 9:53 PM UTC
fe82bf0f06afb032e390220a9bb43fa213460f5307e289406dbeea9caa7a89d1RUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 chown triton-server:triton-server /opt/tritonserver/backends
11/20/2025 9:53 PM UTC
e4ae912825e0df0c0296b7dd256ce41ed0265b5ea6d32a00eed6e41aaae97f7cCOPY
--chown=1000:1000 /opt/tritonserver/backends/python /opt/tritonserver/backends/python
11/20/2025 9:53 PM UTC
4edb2f8b32d4f9571ba45df43fc47656411765d129ab69eba181ec02fd03d0f3COPY
--chown=1000:1000 /opt/tritonserver/backends/identity /opt/tritonserver/backends/identity
11/20/2025 9:53 PM UTC
ab45fc1afd51d6e8a1d18b9fd46decea52da6c7a6183cf9781ceac85b110299dCOPY
--chown=1000:1000 /opt/tritonserver/backends/pytorch /opt/tritonserver/backends/pytorch
11/20/2025 9:53 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.