Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac. Parent comment
mmap benchmark did basically page touch experiment and cold reads were much slower, unfortunately (10ms vs 3ms)
I tried MADV_WILLNEED, F_RDADVISE and preadv. preadv reduced parallelism because requested experts are rarely adjacent in the file.
pread is still the fastest. And I think Flash-Moe got the same result too
There are no comments on this comment yet.
mmap benchmark did basically page touch experiment and cold reads were much slower, unfortunately (10ms vs 3ms)
I tried MADV_WILLNEED, F_RDADVISE and preadv. preadv reduced parallelism because requested experts are rarely adjacent in the file.
pread is still the fastest. And I think Flash-Moe got the same result too