INNER CODE UNIT · Python

decode_request

CerebriumAI/examples · 10-batching/1-litserve-batching-cpu/main.py:10

    def decode_request(self, request):
        print("decode_request")
        return np.asarray(request["input"])

    def predict(self, x):
        print("predict")
        result = self.model(x)
        return result

    def encode_response(self, output):
        print("encode_response")
        return {"output": output}


api = SimpleBatchedAPI()
server = ls.LitServer(api, max_batch_size=3, batch_timeout=20)
app = server.app

View source record →