Integrating TensorFlow Serving ANNC

The TensorFlow Serving ANNC feature integrates with the TensorFlow inference framework and Accelerated Linear Algebra (XLA) through compilation options and code patches. It introduces optimizations tailored for the Kunpeng platform, such as TensorFlow graph fusion, XLA graph fusion, and operator optimization. This section describes how to use the features.

For details about how to enable features of the TensorFlow Serving ANNC, see the TensorFlow Inference Optimization Feature Introduction.