Comparison
Attention vs Sliding-Window Attention
Attention and Sliding-Window Attention are both common AI/LLM terms but cover different ideas. Here is a quick side-by-side.
When you would reach for Attention
Attention comes up when the question is fundamentally about architecture.
Translating "the bank by the river": attention helps "bank" attend more to "river" than to "money".
When you would reach for Sliding-Window Attention
Sliding-Window Attention comes up when the question is fundamentally about architecture.
Mistral 7B: sliding window of 4096 over a 32K-trained context.
Frequently asked
What is the difference between Attention and Sliding-Window Attention?
Attention: Attention is the mechanism a transformer uses to decide which earlier tokens matter most when producing each new one. It mixes information across positions by weighted sum. Sliding-Window Attention: Sliding-window attention limits each token to attending only the most recent W tokens (e.g. 4K), making attention linear in sequence length. Mistral and Gemma use it.
When should I use Attention vs Sliding-Window Attention?
Attention is the right concept when you are focused on architecture. Sliding-Window Attention applies when you are focused on architecture.
Are Attention and Sliding-Window Attention the same thing?
No. Attention is architecture; Sliding-Window Attention is architecture. They are related but address different parts of the AI stack.