Offline

Python Profiling – The Hitchhiker's Guide to Profiling

Track:
Data Engineering and MLOps
Type:
Talk
Level:
intermediate
Room:
S2
Start:
15:25 on Wednesday, 15 July 2026
End:
15:55 on Wednesday, 15 July 2026
Duration:
30 minutes
View in the schedule

Abstract

Want to know what makes your data pipeline slow? How much memory does it use? In this talk, we'll guide you through the landscape of Python profilers – from classics like Scalene, py-spy and memray to newer tools like Tachyon and eBPF profiling – and show you how to choose the right one for your needs.

We'll cover timing and memory profiling methodologies, compare tools across accuracy and overhead, walk through real usage examples, and explore continuous profiling. Whether you're optimizing a single script or debugging production systems, you'll leave with a practical framework for profiling smarter.