• HN Mail
  • Subscribe

CPP

Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp
294 points | 43 comments

llama.cpp
259 points | 114 comments

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

Cppdashboard.dev – The aggregator of what matters in C++
2 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

C++26: Embed
3 points | 0 comments