Triton Inference Server

riton Inference Server provides a cloud inferencing solution optimized for both CPUs and GPUs. Triton provides an inference service via an HTTP/REST or GRPC endpoint, allowing remote clients to request inferencing for any model being managed by the server. For edge deployments, Triton is also available as a shared library with a C API that allows the full functionality of Triton to be included directly in an application.

What’s New In 2.3.0


  • Multiple framework support. Triton can manage any number and mix of models (limited by system disk and memory resources). Supports TensorRT, TensorFlow GraphDef, TensorFlow SavedModel, ONNX, PyTorch, and Caffe2 NetDef model formats. Both TensorFlow 1.x and TensorFlow 2.x are supported. Also supports TensorFlow-TensorRT and ONNX-TensorRT integrated models. Variable-size input and output tensors are allowed if supported by the framework. See Capabilities for information for each framework.

  • Concurrent model execution support. Multiple models (or multiple instances of the same model) can run simultaneously on the same GPU.

  • Batching support. For models that support batching, Triton can accept requests for a batch of inputs and respond with the corresponding batch of outputs. Triton also supports multiple scheduling and batching algorithms that combine individual inference requests together to improve inference throughput. These scheduling and batching decisions are transparent to the client requesting inference.

  • Custom backend support. Triton allows individual models to be implemented with custom backends instead of by a deep-learning framework. With a custom backend a model can implement any logic desired, while still benefiting from the CPU and GPU support, concurrent execution, dynamic batching and other features provided by Triton.

  • Ensemble support. An ensemble represents a pipeline of one or more models and the connection of input and output tensors between those models. A single inference request to an ensemble will trigger the execution of the entire pipeline.

  • Multi-GPU support. Triton can distribute inferencing across all system GPUs.

  • Triton provides multiple modes for model management. These model management modes allow for both implicit and explicit loading and unloading of models without requiring a server restart.

  • Model repositories may reside on a locally accessible file system (e.g. NFS), in Google Cloud Storage or in Amazon S3.

  • HTTP/REST and GRPC inference protocols based on the community developed KFServing protocol.

  • Readiness and liveness health endpoints suitable for any orchestration or deployment framework, such as Kubernetes.

  • Metrics indicating GPU utilization, server throughput, and server latency. The metrics are provided in Prometheus data format.

  • C library inferface allows the full functionality of Triton to be included directly in an application.

Indices and tables