Pinned Loading

1. pytorch/pytorch pytorch/pytorch Public

   Tensors and Dynamic neural networks in Python with strong GPU acceleration

   Python 86.2k 23.2k

2. tpa_pytorch tpa_pytorch Public

   Simple (slightly optimized) implementation of Tensor Product Attention from the T6 paper with a KV cache

   Python 1

3. mla_pytorch mla_pytorch Public

   Simple implementation of Multi Latent Attention from the Deepseek V2 paper https://arxiv.org/abs/2405.04434

   Python 1