Open Source Summit Europe 2022

Both data processing platforms and deep learning frameworks are evolving in their own fields. Usually, Spark is used for offline data processing, and then various deep learning frameworks are used for data inference. A simplified API for DL ​​Inferencing is very important as a bridge. What does an ideal data and deep learning inference pipeline look like? We'll discuss how to build your AI application using Spark and ONNX, the current status and initial idea of Spark commiunty to improve this pipeline, and also make full use of the capabilities of Ascend Hardware Platform. This session will include below parts: - Introduce Current status and plan for onnx contritbution of Ascend Hardware Platform. - Introduce "SPIP: Simplified API for DL Inferencing" background in the Spark community - A simple demo to show how it works. This topic help you know the latest progress of Ascend Hardware Platform integration in ONNX, as well as the initial idea of the inference pipeline improvement in the Spark community.