NVIDIA TensorRT Inference Server¶
The NVIDIA TensorRT Inference Server (TRTIS) provides a cloud inferencing solution optimized for NVIDIA GPUs. The server provides an inference service via an HTTP or gRPC endpoint, allowing remote clients to request inferencing for any model being managed by the server.
What’s New In 0.10.0 Beta¶
- Custom backend support. TRTIS 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 GPU support, concurrent execution, dynamic batching and other features provided by TRTIS.
The inference server provides the following features.
- Multiple framework support. The server can manage any number and mix of models (limited by system disk and memory resources). Supports TensorRT, TensorFlow GraphDef, TensorFlow SavedModel and Caffe2 NetDef model formats. Also supports TensorFlow-TensorRT integrated models.
- TRTIS monitors the model repository for any change and dynamically reloads the model(s) when necessary, without requiring a server restart. Models and model versions can be added and removed, and model configurations can be modified while the server is running.
- Multi-GPU support. TRTIS can distribute inferencing across all system GPUs.
- 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, the server can accept requests for a batch of inputs and respond with the corresponding batch of outputs. TRTIS also supports dynamic batching where individual inference requests are dynamically combined together to improve inference throughput. Dynamic batching is transparent to the client requesting inference.
- Model repositories may reside on a locally accessible file system (e.g. NFS) or in Google Cloud Storage.
- Readiness and liveness health endpoints suitable for any orchestration or deployment framework, such as Kubernetes.
- Metrics indicating GPU utiliization, server throughput, and server latency.
- Installing the Server
- Running the Server
- Client Libraries and Examples
- Model Repository
- Model Configuration
- Inference Server API