Just a small fix to include proper llama-swap binary when building the arm64 architecture.
- set up a GHA scheduled job to build the container nightly - enabling pushing a llama-swap:unified and a llama-swap:unified-Y-M-D image to ghcr.io - tidy up Dockerfile to use a non-root user and llama-swap as an entry point
Add Docker build scripts for a unified cuda docker container with llama-server, stable-diffusion.cpp, whisper.cpp.
Damir
Benson Wong