TRITONSERVER

Description

tritonserver website

Triton Inference Server provides a cloud and edge inferencing solution optimized for both CPUs and GPUs. Triton supports an HTTP/REST and GRPC protocol that allows remote clients to request inferencing for any model being managed by the server. For edge deployments, Triton is available as a shared library with a C API that allows the full functionality of Triton to be included directly in an application. This container was downloaded from NVIDIA GPU Cloud. It cannot be modified. No new packages can be added to this installation. Use the core tritonserver module when requesting package addition. NGC Singularity container: 23.01-py3.sif Usage: ml purge ml tritonserver/23.01 tritonserver

Environment Modules

Run module spider tritonserver to find out what environment modules are available for this application.

Environment Variables

• HPC_TRITONSERVER_DIR - installation directory

Categories

machine_learning