Shortcuts

TorchServe gRPC API

Note: Current TorchServe gRPC does not support workflow.

TorchServe also supports gRPC APIs for both inference and management calls.

TorchServe provides following gRPCs apis

  • Inference API

    • Ping : Gets the health status of the running server

    • Predictions : Gets predictions from the served model

    • StreamPredictions : Gets server side streaming predictions from the saved model

  • Management API

    • RegisterModel : Serve a model/model-version on TorchServe

    • UnregisterModel : Free up system resources by unregistering specific version of a model from TorchServe

    • ScaleWorker : Dynamically adjust the number of workers for any version of a model to better serve different inference request loads.

    • ListModels : Query default versions of current registered models

    • DescribeModel : Get detail runtime status of default version of a model

    • SetDefault : Set any registered version of a model as default version

By default, TorchServe listens on port 7070 for the gRPC Inference API and 7071 for the gRPC Management API. To configure gRPC APIs on different ports refer configuration documentation

Python client example for gRPC APIs

Run following commands to Register, run inference and unregister, densenet161 model from TorchServe model zoo using gRPC python client.

git clone --recurse-submodules https://github.com/pytorch/serve
cd serve
  • Install gRPC python dependencies

pip install -U grpcio protobuf grpcio-tools googleapis-common-protos
  • Start torchServe

mkdir models
torchserve --start --model-store models/
  • Generate python gRPC client stub using the proto files

python -m grpc_tools.protoc -I third_party/google/rpc --proto_path=frontend/server/src/main/resources/proto/ --python_out=ts_scripts --grpc_python_out=ts_scripts frontend/server/src/main/resources/proto/inference.proto frontend/server/src/main/resources/proto/management.proto
  • Register densenet161 model

python ts_scripts/torchserve_grpc_client.py register densenet161
  • Run inference using

python ts_scripts/torchserve_grpc_client.py infer densenet161 examples/image_classifier/kitten.jpg
  • Unregister densenet161 model

python ts_scripts/torchserve_grpc_client.py unregister densenet161

GRPC Server Side Streaming

TorchServe GRPC APIs adds a server side streaming of the inference API “StreamPredictions” to allow a sequence of inference responses to be sent over the same GRPC stream. This new API is only recommended for use case when the inference latency of the full response is high and the inference intermediate results are sent to client. An example could be LLMs for generative applications, where generating “n” number of tokens can have high latency, in this case user can receive each generated token once ready until the full response completes. This new API automatically forces the batchSize to be one.

service InferenceAPIsService {
    // Check health status of the TorchServe server.
    rpc Ping(google.protobuf.Empty) returns (TorchServeHealthResponse) {}

    // Predictions entry point to get inference using default model version.
    rpc Predictions(PredictionsRequest) returns (PredictionResponse) {}

    // Streaming response for an inference request.
    rpc StreamPredictions(PredictionsRequest) returns (stream PredictionResponse) {}
}

Backend handler calls “send_intermediate_predict_response” to send one intermediate result to frontend, and return the last result as the existing style. For example

from ts.handler_utils.utils import send_intermediate_predict_response
''' Note: TorchServe v1.0.0 will deprecate
"from ts.protocol.otf_message_handler import send_intermediate_predict_response".
Please replace it with "from ts.handler_utils.utils import send_intermediate_predict_response".
'''

def handle(data, context):
    if type(data) is list:
        for i in range (3):
            send_intermediate_predict_response(["intermediate_response"], context.request_ids, "Intermediate Prediction success", 200, context)
        return ["hello world "]

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources