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
b335e107d2c989a2339a2d9bc41146265f92402db7e503c435977be7ee3b408aCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
01/27/2026 11:08 PM UTC
5ff43a6759fb545ed68af03a32db5fbb9ae940da79e180540b96b09d2f65567aLABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
01/27/2026 11:08 PM UTC
55b9ac6553918648b2aff3c184cf794af42ddbdbacde8e62fa6485c57d08a968RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 chown triton-server:triton-server /opt/tritonserver/caches
01/27/2026 11:08 PM UTC
80d50eb5e8b20da4a17708edf0d753121d8b40a9e23e0c668a58e39cbaf612deCOPY
--chown=1000:1000 /opt/tritonserver/caches/local /opt/tritonserver/caches/local
01/27/2026 11:08 PM UTC
69e46ec91bab6e57f939da39e02f438df9d0c3c01f0b38d17cd53ad3a9140301RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 chown triton-server:triton-server /opt/tritonserver/repoagents
01/27/2026 11:08 PM UTC
72237c6e813ea7b5f9fa57812f35dcefdc0d76575388a45fd571aa2cf4895c1cCOPY
--chown=1000:1000 /opt/tritonserver/repoagents/checksum /opt/tritonserver/repoagents/checksum
01/27/2026 11:08 PM UTC
8861e6933f2723a62034717b84e03a6d119cf827a1acfd61746177e727b2f7baRUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 chown triton-server:triton-server /opt/tritonserver/backends
01/27/2026 11:08 PM UTC
020f517bfd44e5fd300d03f9a69be0e3435d7efd20bfe2fdf836030cc6c8a65eCOPY
--chown=1000:1000 /opt/tritonserver/backends/python /opt/tritonserver/backends/python
01/27/2026 11:08 PM UTC
9b1a961830feef64ab8872513dd7ba1da6c963dd1a2afe02c0a7a1173c14eb55COPY
--chown=1000:1000 /opt/tritonserver/backends/identity /opt/tritonserver/backends/identity
01/27/2026 11:08 PM UTC
56e2ff5a8d9a0fd9fc9db84a9802062c0c5b13b59268192f5b2004294a6d8708COPY
--chown=1000:1000 /opt/tritonserver/backends/pytorch /opt/tritonserver/backends/pytorch
01/27/2026 11:08 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.