# optional, If name is specified it must match the name of the model repository directory containing the model. name: "runtime" backend: "fastdeploy" max_batch_size: 16 # Input configuration of the model input [ { # input name name: "images" # input type such as TYPE_FP32、TYPE_UINT8、TYPE_INT8、TYPE_INT16、TYPE_INT32、TYPE_INT64、TYPE_FP16、TYPE_STRING data_type: TYPE_FP32 # input shape, The batch dimension is omitted and the actual shape is [batch, c, h, w] dims: [ 3, -1, -1 ] } ] # The output of the model is configured in the same format as the input output [ { name: "output0" data_type: TYPE_FP32 dims: [ -1, -1 ] } ] # Number of instances of the model instance_group [ { # The number of instances is 1 count: 1 # Use CPU, GPU inference option is:KIND_GPU kind: KIND_CPU } ] optimization { execution_accelerators { cpu_execution_accelerator : [ { # use ONNXRuntime engine name: "onnxruntime", # set cpu threads parameters { key: "cpu_threads" value: "4" } }] }}