lucidrains / flash-cosine-sim-attention
Implementation of fused cosine similarity attention in the same style as Flash Attention
☆207Updated last year
Related projects ⓘ
Alternatives and complementary repositories for flash-cosine-sim-attention
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆362Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆222Updated 2 years ago
- Implementation of a Transformer, but completely in Triton☆248Updated 2 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆247Updated 2 years ago
- Implementation of Flash Attention in Jax☆196Updated 8 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 3 months ago
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆194Updated 9 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆90Updated 3 months ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 2 years ago
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆179Updated last year
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆124Updated 2 years ago
- Implementation of a U-net complete with efficient attention as well as the latest research findings☆267Updated 6 months ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆43Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆95Updated last year
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆94Updated last month
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆226Updated 2 months ago
- A library for unit scaling in PyTorch☆105Updated 2 weeks ago
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆84Updated 2 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆116Updated 3 years ago
- Implementation of Block Recurrent Transformer - Pytorch☆213Updated 3 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆247Updated 6 months ago
- Implementation of Fast Transformer in Pytorch☆171Updated 3 years ago
- ☆164Updated last year
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- Implementation of Linformer for Pytorch☆257Updated 10 months ago
- Named tensors with first-class dimensions for PyTorch☆322Updated last year
- Contrastive Language-Image Pretraining☆143Updated 2 years ago
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆77Updated 10 months ago