Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Jiaming, Zhao, Yilong, Zhu, Kan, Xiao, Guangxuan, Kasikci, Baris, Han, Song
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916370490327040
author Tang, Jiaming
Zhao, Yilong
Zhu, Kan
Xiao, Guangxuan
Kasikci, Baris
Han, Song
author_facet Tang, Jiaming
Zhao, Yilong
Zhu, Kan
Xiao, Guangxuan
Kasikci, Baris
Han, Song
contents As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases significantly as the sequence length grows. This slowdown is primarily caused by loading a large KV cache during self-attention. Previous works have shown that a small portion of critical tokens will dominate the attention outcomes. However, we observe the criticality of a token highly depends on the query. To this end, we propose Quest, a query-aware KV cache selection algorithm. Quest keeps track of the minimal and maximal Key values in KV cache pages and estimates the criticality of a given page using Query vectors. By only loading the Top-K critical KV cache pages for attention, Quest significantly speeds up self-attention without sacrificing accuracy. We show that Quest can achieve up to 2.23x self-attention speedup, which reduces inference latency by 7.03x while performing well on tasks with long dependencies with negligible accuracy loss. Code is available at http://github.com/mit-han-lab/Quest .
format Preprint
id arxiv_https___arxiv_org_abs_2406_10774
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Tang, Jiaming
Zhao, Yilong
Zhu, Kan
Xiao, Guangxuan
Kasikci, Baris
Han, Song
Computation and Language
Machine Learning
As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases significantly as the sequence length grows. This slowdown is primarily caused by loading a large KV cache during self-attention. Previous works have shown that a small portion of critical tokens will dominate the attention outcomes. However, we observe the criticality of a token highly depends on the query. To this end, we propose Quest, a query-aware KV cache selection algorithm. Quest keeps track of the minimal and maximal Key values in KV cache pages and estimates the criticality of a given page using Query vectors. By only loading the Top-K critical KV cache pages for attention, Quest significantly speeds up self-attention without sacrificing accuracy. We show that Quest can achieve up to 2.23x self-attention speedup, which reduces inference latency by 7.03x while performing well on tasks with long dependencies with negligible accuracy loss. Code is available at http://github.com/mit-han-lab/Quest .
title Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2406.10774