linrrzqqq commented on PR #68666: URL: https://github.com/apache/doris/pull/68666#issuecomment-6260346501
`execute_impl` will be called by multiple threads concurrently(generally, threads num is half of CPU cores), so `ai_max_concurrency * CPU cores / 2` threads will be used to call AI api for a single AI function. It is not our expectation. I think you can try to change `ai_contextxs_window_size` or ``parallel_pipeline_task_num` to improve performance. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
