aclmdlSetConfigOpt

Applicability

Product

Supported

Atlas A3 training products/Atlas A3 inference products

Atlas A2 training products/Atlas A2 inference products

Atlas 200I/500 A2 inference products

Atlas inference products

Atlas training products

Description

Set the value of an attribute in the configuration object for loading a model, including the model execution priority, model file directory or memory address, and memory size.

This API needs to work with the following APIs to load models:
  1. Call aclmdlCreateConfigHandle to create a configuration object for loading a model.
  2. (Optional) Call aclmdlSetExternalWeightAddress to configure device memory for storing external weights.
  3. Call aclmdlSetConfigOpt multiple times to set the value of each attribute in the configuration object.
  4. Call aclmdlLoadWithConfig to specify the configuration information for model loading and load your model.
  5. After the model is successfully loaded, call aclmdlDestroyConfigHandle to destroy the configuration object.

Prototype

aclError aclmdlSetConfigOpt(aclmdlConfigHandle *handle, aclmdlConfigAttr attr, const void *attrValue, size_t valueSize)

Parameters

Parameter

Input/Output

Description

handle

Output

Pointer to the configuration object for loading a model. Call aclmdlCreateConfigHandle to create an object in advance.

attr

Input

Attribute to set.

attrValue

Input

Pointer to the attr value to set.

If the attribute value itself is a pointer, pass the address of the pointer.

valueSize

Input

Data length of attrValue.

You can use the sizeof(*attrValue) function in the C/C++ standard library to query the data length.

Returns

0 on success; else, failure. For details, see aclError.

See Also

For model loading by using aclmdlSetConfigOpt and aclmdlLoadWithConfig, the caller needs to set the attributes in the configuration object passed to the API call to decide how the model will be loaded and who will manage the memory.

By choosing from the following APIs, you can directly determine whether to load a model from a file or from memory and whether the memory is managed by the system or the user.