Classic

Request: optimized implementation of GOBIG (txt2imghd and img2imghd)

2

This is a very powerful tool, it would be nice to see it implemented using the optimized code: https://github.com/jquesnelle/txt2imghd

Feature Request: Add message complete feature to chat UI

1

The ability to write the start of a message in chat mode and then send it off to the model for it to complete the rest would be very useful....

Using llama.cpp, the entire context gets reprocessed each generation

18

When using llama.cpp, the entire prompt gets processed at each generation making things like chat mode unbearably slow. The problem compounds as the context gets larger and larger as well....