CPP

llama.cpp
363 points | 165 comments

Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp
306 points | 42 comments

DLLM: Minimal, clean coding agent built directly on llama.cpp without overhead
9 points | 3 comments

Show HN: Cjson.cpp, the new fastest-ever (constexpr) JSON parser
3 points | 0 comments

Privibe - LLM Cli Local first+privacy focus+llama.cpp cache branch + Qwen3.x
2 points | 1 comments

Show HN: FEDERaiDE, a TUI harness with P2P multi-agent routing and built in IDE
3 points | 0 comments

Soup Raiders goes native: What you gain by building your own game engine
56 points | 56 comments