Function serve

backend/python/llama-cpp-quantization/backend.py:404–417

(address)

def serve(address):
    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
        interceptors=get_auth_interceptors(),
    )
    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
    server.add_insecure_port(address)
    server.start()
    print(f"Quantization backend listening on {address}", file=sys.stderr, flush=True)

    try:
        while True:
            time.sleep(_ONE_DAY_IN_SECONDS)
    except KeyboardInterrupt:
        server.stop(0)


if __name__ == "__main__":