AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Fast and memory-efficient exact attention

Solve puzzles. Improve your pytorch.

MMseqs2: ultra fast and sensitive search and clustering suite

A code-searching tool similar to ack, but faster.

v objective diffusion inference code for PyTorch.

Open source code for AlphaFold.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2