From a331a27dce1d48f535c1efbce06e74eda049399e Mon Sep 17 00:00:00 2001 From: "jh.song" Date: Thu, 26 Feb 2026 02:04:18 +0800 Subject: [PATCH] docs: add a reading to week 2 flash attention --- book/src/week2-04-flash-attention.md | 1 + 1 file changed, 1 insertion(+) diff --git a/book/src/week2-04-flash-attention.md b/book/src/week2-04-flash-attention.md index 4d97f78..37d2cfd 100644 --- a/book/src/week2-04-flash-attention.md +++ b/book/src/week2-04-flash-attention.md @@ -4,6 +4,7 @@ In this chapter, we will implement Flash Attention 2 for the Week 2 Qwen2 servin **📚 Readings** +- [From Online Softmax to FlashAttention](https://courses.cs.washington.edu/courses/cse599m/23sp/notes/flashattn.pdf) - [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://arxiv.org/abs/2205.14135) - [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://arxiv.org/abs/2307.08691) - [MLX Extension Development Guide](https://ml-explore.github.io/mlx/build/html/dev/extensions.html)