RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

[NeurIPS 2024] Official code of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“

The semantic segmentation of remote sensing images

Implementation of Agent Attention in Pytorch

Explorations into the recently proposed Taylor Series Linear Attention

CUDA implementation of autoregressive linear attention, with all the latest research findings

The semantic segmentation of remote sensing images

Official Implementation of SEA: Sparse Linear Attention with Estimated Attention Mask (ICLR 2024)

[ICML 2024] Official implementation of "LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions."

Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)

Implementation of: Hydra Attention: Efficient Attention with Many Heads (https://arxiv.org/abs/2209.07484)