to some extent in the detailed arch: https://github.com/nuclio/nuclio/blob/master/docs/architectu... The point is that there is a lot of parallelism, reduced locks and context switches, zero-copy and buffer reuse (less GC), async IO, Etc. things that most developers wont implement (unless they are perf optimization savvy), so you get that for free and can run 400K events/sec on a process using standard server (with Go functions)