Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Out of curiosity, do the LLMs all use memory safe languages?




Llama.cpp is called Llama.cpp, so there’s that…

Whenever the public has heard about the language it's always been Python.

The language that implements Python's high-speed floating point has often been FORTRAN.

https://fortranwiki.org/fortran/show/Python


With lots of CUDA C++ libraries, among others.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: