200 lines Flash Attention (only forward pass) in CUDA.
-
Updated
Feb 23, 2025 - Cuda
#
flashattention
Here are 3 public repositories matching this topic...
FlashAttention-2 in Triton for sliding window attention (fwd + bwd pass)
-
Updated
Mar 6, 2025 - Python
This repository contains multiple implementations of Flash Attention optimized with Triton kernels, showcasing progressive performance improvements through hardware-aware optimizations. The implementations range from basic block-wise processing to advanced techniques like FP8 quantization and prefetching
-
Updated
Apr 8, 2025 - Python
Improve this page
Add a description, image, and links to the flashattention topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the flashattention topic, visit your repo's landing page and select "manage topics."