CPP

LlamaLib: A cross-platform C++/C# library for local LLMs based on llama.cpp
4 points | 0 comments

Claude is autonomously livecoding a major port (CPP –> WebGPU)
2 points | 1 comments

Llama.cpp performance breakthrough for multi-GPU setups
1 points | 0 comments

Show HN: Notebook page on llama.cpp official webui
1 points | 0 comments

Ask HN: How to share local models between tools?
2 points | 0 comments

Show HN: Peen – A minimal coding agent CLI built for local models
1 points | 1 comments

Goodbye Smartwatches, Hello Health AI on Your Wrist
1 points | 1 comments