Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Open standard for machine learning interoperability

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Ongoing research training transformer models at scale

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to …

⚡ Competitive Programming Library

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)

A tensorflow implementation of Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

Graph dump of torchbench models, huggingface models, and TIMM models.