Tuning in Offline Inference Scenarios

Tuning Workflow
Environment Setup
Environment Variable Configuration
Before using AOE for tuning, run the export command to declare environment variables on the current terminal. Configurations in this mode become invalid after the shell terminal is closed. You can also write the commands for configuring environment variables to the custom script for future use.
Quick Start
This section describes how to quickly perform AOE tuning on models trained on different frameworks. The following uses operator tuning as an example. If subgraph tuning is required, change the value of job_type in the command to 1.
Tuning Procedure
This section provides tuning command examples in offline inference scenarios.
Tuning Result Viewing
This section introduces how to view the results of tuning once it is complete, including information displayed on the screen and the generated custom repository, .om model, operator tuning result file, and subgraph tuning result file.
Performance Verification

Parent topic: AOE (Ascend EP)