A developer built a C99 inference engine that runs DeepSeek-V4-Flash, a 284B-parameter mixture-of-experts model, on a laptop with just 3.2GB of RAM by streaming weights off NVMe and caching only the e…
A developer released NanoEuler, a GPT-2-scale language model built entirely from scratch in C/CUDA without any machine learning libraries. The project includes a hand-written byte-level BPE tokenizer,…
A Fortran programmer documented using LLMs and agentic workflows to write GPU-accelerated Fortran code, with posts on software architecture, OpenMP target offloading, and standard parallelism. The pro…
Guardog, a zero-copy C/Python DFA engine, scrubs logs at 571 MB/s, operating 14.4x faster than standard Python regex by bypassing the GIL and using in-place memory mutation. The engine is available fo…