Triton

vllmvllm-project/vllm

A high-throughput, memory-efficient inference and serving engine for large language models (LLMs).

annotated_deep_learning_paper_implementationslabmlai/annotated_deep_learning_paper_implementations

A collection of 60+ annotated PyTorch implementations of deep learning papers with side-by-side explanatory notes.

unslothunslothai/unsloth

A web UI and optimization library for running and fine-tuning open-source AI models locally with 2x faster training and 70% less VRAM.