Hugging Face Trending Papers

Training-Free Hashing-Based Attention via Binary Principal Components

Read the original on Hugging Face Trending Papers →

Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches. Existing sparse attention reduce computation by attending to fewer KV pairs, but often suffer from substantial accuracy degradation, require additional training, or rely on expensive hashing.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 6

Training-Free Hashing-Based Attention via Binary Principal Components

arXiv:2608. 04405v1 Announce Type: cross Abstract: Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches.

By Daohai Yu, Zhanpeng Zeng, Keyu Chen, Wenhao Li, Zhifeng Shen, Luxi Lin, Ruizhi Qiao, Xing Sun, Rongrong Ji
arXiv Machine Learning
Jul 1

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

arXiv:2606. 31519v1 Announce Type: new Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased.

By Wenhao Li, Jinhao Dong, Hailin Zhang, Wenhang Shi, Wei Lu, Xiaoyong Du