Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 37 tok/s
Gemini 2.5 Pro 44 tok/s Pro
GPT-5 Medium 14 tok/s Pro
GPT-5 High 14 tok/s Pro
GPT-4o 90 tok/s Pro
Kimi K2 179 tok/s Pro
GPT OSS 120B 462 tok/s Pro
Claude Sonnet 4 37 tok/s Pro
2000 character limit reached

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys (2403.02352v1)

Published 1 Mar 2024 in cs.LG and cs.AI

Abstract: We propose a new attention mechanism with linear complexity, ATP, that fixates \textbf{A}ttention on \textbf{T}op \textbf{P}rincipal keys, rather than on each individual token. Particularly, ATP is driven by an important observation that input sequences are typically low-rank, i.e., input sequences can be represented by a few principal bases. Therefore, instead of directly iterating over all the input tokens, ATP transforms inputs into an orthogonal space and computes attention only on the top principal bases (keys). Owing to the observed low-rank structure in input sequences, ATP is able to capture semantic relationships in input sequences with a few principal keys. Furthermore, the attention complexity is reduced from \emph{quadratic} to \emph{linear} without incurring a noticeable performance drop. ATP further reduces complexity for other linear layers with low-rank inputs, leading to more speedup compared to prior works that solely target the attention module. Our evaluations on various models (e.g., BERT and Llama) demonstrate that ATP achieves comparable accuracy with much lower computation and memory complexity than the standard attention mechanism. In particular, ATP barely loses accuracy with only $1/2$ principal keys, and only incurs around $2\%$ accuracy drops with $1/4$ principal keys.

Citations (1)
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

Summary

We haven't generated a summary for this paper yet.

Dice Question Streamline Icon: https://streamlinehq.com

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.