CPP

The Llama.cpp Fork That Enables Qwen 3.8 27B Large Contexts for 16GB VRAM GPU
5 points | 2 comments

Show HN: VelocityNote – A tiny Markdown notebook with local AI
2 points | 1 comments

Show HN: Don't trust me bro: fixing GPT-OSS (3.49B tokens, 1k GPU hours, 1x3090)
2 points | 0 comments

C++26: Standard Library Hardening Experiments
89 points | 53 comments

Move in C++ without a std:move
6 points | 2 comments

C++26: Std:Inplace_vector
6 points | 0 comments

Bringing Package Management to Swift's C++ Interoperability
3 points | 0 comments