xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

VideoSys: An easy and efficient system for video generation

Ongoing research training transformer models at scale

SGLang is a fast serving framework for large language models and vision language models.

NumPy & SciPy for GPU

Accelerating Diffusion Transformers with Token-wise Feature Caching

Minimalist ML framework for Rust

FlashMLA: Efficient MLA decoding kernels

Tile primitives for speedy kernels