Viewing profile — samber

Comparing compute cost versus FlashAttention-2 is not very honest to me. FlashAttention-2 is not used anymore for at least 2y. This architecture would have been a massive improveme…

According to Subquadratic, Needle in a Haystack is strong up to 12m tokens, but RULER has not been tested above 128k tokens ??

OMG. I'm going to recode some of my libraries.

35+ atomic skills covering all aspects of the language (conventions, common errors, top libraries, testing, benchmarks, performance, troubleshooting, etc.). Benchmarks I ran on Opu…

IMO, this is much more readable. So many Go developers ignore some tools because they consider them "not idiomatic". But why not use abstractions when available ??? Did we forget t…

`do` builder here After 2y in beta, I’ve just released v2 of “do”, the dependency injection toolkit for Golang. This major version introduces a new scope-based architecture, transi…