sail.MultiEngine
________________

MultiEngine
>>>>>>>>>>>>>>>

**Interface:**
    .. code-block:: python

        def __init__(self, 
                    bmodel_path: str, 
                    device_ids: list[int], 
                    sys_out: bool = True, 
                    graph_idx: int = 0)

**Parameters**

* bmodel_path : str

Path to bmodel

* device_ids : list[int]    

TPU ID. You can use bm-smi to see available IDs

* sys_out : bool, default: True

The flag of copy result to system memory.

* graph_idx : int, default: 0

The specified graph index


set_print_flag
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Print debug messages.

**Interface:**
    .. code-block:: python

        def set_print_flag(self, print_flag: bool)
 

**Parameters**

* print_flag : bool

if print_flag is true, print debug messages


set_print_time
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Print main process time use.

**Interface:**
    .. code-block:: python
        
        def set_print_time(self, print_flag: bool)
 

**Parameters**

* print_flag : bool

if print_flag is true, print main process time use, Otherwise not print.


get_device_ids
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get device ids of this MultiEngine.

**Interface:**
    .. code-block:: python

        def get_device_ids(self)-> list[int] 
 
            
**Returns**

* device_ids : list[int]    

tpu ids of this MultiEngine.


get_graph_names
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get all graph names in the loaded bmodels.

**Interface:**
    .. code-block:: python

        def get_graph_names(self)-> list
 

**Returns**

* graph_names : list

Graph names list in loaded context


get_input_names
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get all input tensor names of the specified graph.

**Interface:**
    .. code-block:: python

        def get_input_names(self, graph_name: str)-> list
 

**Parameters**

* graph_name : str

Specified graph name

**Returns**

* input_names : list

All the input tensor names of the graph


get_output_names
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get all output tensor names of the specified graph.

**Interface:**
    .. code-block:: python

        def get_output_names(self, graph_name: str)-> list
 

**Parameters**

* graph_name : str

Specified graph name

**Returns**

* input_names : list

All the output tensor names of the graph


get_input_shape
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get the maximum dimension shape of an input tensor in a graph. \
There are cases that there are multiple input shapes in one input name, \
This API only returns the maximum dimension one for the memory allocation \
in order to get the best performance.

**Interface:**
    .. code-block:: python

        def get_input_shape(self, graph_name: str, tensor_name: str)-> list
 

**Parameters**

* graph_name : str

The specified graph name

* tensor_name : str

The specified input tensor name

**Returns**

* tensor_shape : list

The maxmim dimension shape of the tensor


get_output_shape
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Get the shape of an output tensor in a graph.

**Interface:**
    .. code-block:: python

        def get_output_shape(self, graph_name: str, tensor_name: str)-> list
 

**Parameters**

* graph_name : str

The specified graph name

* tensor_name : str

The specified output tensor name

**Returns**

* tensor_shape : list

The shape of the tensor


process
>>>>>>>>>>>>>>>>>>>

Inference with provided system data of input tensors.

**Interface:**
    .. code-block:: python

        def process(self, input_tensors: dict {str : numpy.array})-> dict {str : numpy.array}
 

**Parameters**

* input_tensors : dict {str : numpy.array}

Data of all input tensors in system memory

**Returns**

* output_tensors : dict {str : numpy.array}

Data of all output tensors in system memory