The github release pages for this project have me wondering who it is for. There are multiple releases per day. Also the Linux release binaries do not compile for CUDA.
It's more reasonable for a lot of people to just follow master and build from source.
Didn't expect this to pop up here - please ignore for now. We are preparing official semantic versioning of llama.cpp and it's almost ready, but not quite.
7 comments
[ 7.4 ms ] story [ 73.8 ms ] threadseems like stray tags?
It's more reasonable for a lot of people to just follow master and build from source.
https://github.com/brian-learns/llama_cpp/blob/main/update.s...
More info about the versioning process is here: https://github.com/ggml-org/ggml/discussions/1579