May 18

1. 08:45

   fix: use pre-compiled llama-cpp-python wheel + model in image

   hugh007
   Verified signature

   0408500
2. 08:41

   fix: bake GGUF model into Docker image during build

   hugh007
   Verified signature

   abfbb52
3. 08:28

   fix: use pre-compiled llama-server binary (zero compilation)

   hugh007
   Verified signature

   df05d22
4. 08:22

   fix: use ninja-build + CMAKE_ARGS for llama-cpp-python build

   hugh007
   Verified signature

   e632dcd
5. 07:53

   fix: add cmake+build-essential for llama-cpp

   hezu59158
   6f6d8c1
6. 07:51

   fix: add libgomp1 for llama-cpp runtime

   hezu59158
   51a909e
7. 07:48

   add README.md

   hezu59158
   2271d14
8. 07:17

   opt: use pre-built wheel for faster build

   hezu59158
   7262a86
9. 07:10

   init

   hezu59158
   f776329