AI engineering glossary · Computing foundations
What is latency?
Latency: The time delay between requesting something and getting the result, such as the wait for a network reply or a memory read. It is measured in time units like milliseconds, and low latency matters for interactive applications.
Latency: an example
A ping to a server in Mumbai from Delhi might show 20 ms latency, while one to a US server could show around 200 ms.
Related terms
More Computing foundations terms
Where you learn it
Latency is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.