all agent api update benchmark dataset deployment fine tuning inference library model new model open source optimization prompt engineering quantization rag reinforcement learning research tool training tutorial visualization workflow
Llm.c – LLM training in simple, pure C/CUDA
HN AI Stories · 756d ago · 9 · open source library inference tutorial

llm.c is a high-performance C/CUDA implementation for LLM pretraining that eliminates heavy dependencies (PyTorch, Python) while achieving 7% faster performance than PyTorch Nightly. It provides clean reference implementations for reproducing GPT-2/GPT-3 models with both GPU (CUDA) and CPU code paths, making it valuable for understanding model training mechanics and CUDA optimization.

Llamafile lets you distribute and run LLMs with a single file
HN AI Stories · 887d ago · 8 · tool open source deployment inference

llamafile 0.10.0 update from Mozilla.ai enables distributing and running open LLMs as single-file executables across platforms with no installation required, now with improved alignment to latest llama.cpp versions and support for more recent models. The tool also includes whisperfile for single-file speech-to-text capabilities, making local LLM deployment significantly more accessible for developers.