Metadata
Title
AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs
Category
general
UUID
c8ec31c0dd9e445e9b7da5cd3b26f406
Source URL
https://wsai.iitm.ac.in/preprints/aqua-attention-via-query-magnitudes-for-memory...
Parent URL
https://wsai.iitm.ac.in/preprints/
Crawl Time
2026-03-23T19:10:33+00:00
Rendered Raw Markdown

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs

Source: https://wsai.iitm.ac.in/preprints/aqua-attention-via-query-magnitudes-for-memory-and-compute-efficient-inference-in-llms-30/ Parent: https://wsai.iitm.ac.in/preprints/

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs

https://doi.org/10.48550/arXiv.2509.11155

Authors

S, Santhosh G , Prakash, Saurav , Ravindran, Balaraman

Preprint Server

arXiv

Santhosh G S, Saurav Prakash, Balaraman Ravindran, AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs

Preprint link: https://arxiv.org/abs/2509.11155