Hacker News new | ask | show | jobs
by esafak 17 days ago
That's why I always ask: got benchmarks?
1 comments
zaydmulani 17 days ago
Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table.
link
SwellJoe 17 days ago
I don't care if it's fast, if it makes the model dumber by cluttering up context.
link