Enable AI inferencing on z/OS

Use the zopen package manager (QuickStart Guide) to install:

zopen install llamacpp

1. Clone the repository:

git clone https://github.com/zopencommunity/llamacppport.git
cd llamacppport

2. Build using zopen:

zopen build -vv

See the zopen porting guide for more details.

While building if an error is encountered in the ggml-cpu.cpp file (perhaps related to pthread), run zopen upgrade zoslib -y and try building again.

Contributions are welcome! Please follow the zopen contribution guidelines.