Daily Digest
4 articles published
Articles
antirez (Salvatore Sanfilippo)
Distributing LLM inference in DwarfStar
High end NVIDIA cards, and the server and power needed to run them, cost a lot of money, especially if you plan to reach enough VRAM to run massive models. The alternative, so far, has been Apple hard
Sylvain Kerkour
The problem with Rust for backend services
Rust is not bad for backend services. I'm currently working on a large backend service in Rust and I enjoy it (and a few other smaller). The compiler-enforced correctness and