MindSpore Serving Documents
MindSpore Serving is a lightweight and high-performance service tool, which helps users efficiently deploy online inference services in production environments.
Simply train your model on MindSpore, export it and then use MindSpore Serving to create inference services for the models.
MindSpore Serving supports:
Customized preprocessing and postprocessing to simplify model release and deployment
Batch function that splits and combines multiple-instances requests to fit the batch size requirements of the model
Distributed model inference
gRPC APIs and easy-to-use Python encapsulation APIs on the client
RESTful APIs on the client
Code repository address: <https://gitee.com/mindspore/serving>
Typical Application Scenarios
Use the Add network as an example to demonstrate how to deploy an inference service with MindSpore Serving.
Easily access services with high performance.
Access services based on HTTP.
- MindSpore Serving-based Inference Service Deployment
- MindSpore Serving-based Distributed Inference Service Deployment
- gRPC-based MindSpore Serving Access
- RESTful-based MindSpore Serving Access
- Servable Provided Through Model Configuration
- Service Deployment with Multiple Subgraphs and Stateful Model