Commit History
-
Serve pepekberbulu Q4_K_M GGUF live via llama-server (fast CPU inference)
Verified signature39c322b -
Use prebuilt llama.cpp binary (b9670) instead of compiling (fix OOM)
Verified signature75d6f7a -
Deploy VibeThinker-3B -> GGUF Q4_K_M conversion+upload job
Verified signature6f65232