• HN Mail
  • Subscribe

CPP

llama.cpp
362 points | 162 comments

Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp
305 points | 41 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

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

Show HN: Otaku – A Roleplay Terminal Client
2 points | 0 comments

Understanding std:counting_semaphore and std:binary_semaphore from C++20
4 points | 0 comments