ai-bond/flash-attention-v100

Fast and memory-efficient exact attention

Fast and memory-efficient exact attention

FlashMLA: Efficient Multi-head Latent Attention Kernels

FlashKDA: high-performance Kimi Delta Attention kernels

Helpful tools and examples for working with flex-attention

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

🚀 Efficient implementations for emerging model architectures

Flash Attention Triton kernel with support for second-order derivatives

Implementation of fused cosine similarity attention in the same style as Flash Attention