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

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

procedural reasoning datasets

Animation engine for explanatory math videos

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

You like pytorch? You like micrograd? You love tinygrad! ❤️

A simple tool for visually comparing two PDF files

GPUOcelot: A dynamic compilation framework for PTX