Views
No views yet
1$ git clone -b hailo https://github.com/danbev/llama.cpp.git && cd llama.cpp
2$ cmake -B build -S . -DGGML_HAILO=ON -DGGML_NATIVE=ON
3$ cmake --build build --target llama-cli -j 12$ ./build/bin/llama-cli -hf danbev/hailo-llama-3.2-GGUF