Instructions for compiling from scratch

[RevanthRameshkumar]

Are there any instructions for compiling the dlls from scratch? I am thinking to maybe just run through the GitHub workflow line by line on command line, but I want to make sure I am not missing anything.

My goal is to make changes to the sampling code for some models (like in llama.cc file).

My current guess is that I make the changes, run cmake like in the build.yml and the result appears as ctransformers.dll under the cuda folder in lib?