WeichenXu123 edited a comment on issue #24734: [SPARK-27870][SQL][PySpark] Flush each batch for pandas UDF (for improving pandas UDFs pipeline) URL: https://github.com/apache/spark/pull/24734#issuecomment-497534177 @BryanCutler "Making batch size small" is the ML realtime inference requirement. This is another issue. Such as, input data coming from a stream, we need deal with coming data as soon as possible instead of accumulating a large batch. Under the case "we already choose small batch size", this PR improve the pipeline performance. Thanks!
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
