7 papers · 1 filter
SR: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching
Jialong Han, You Wu, Kewei Tu
The growth of context window lengths in Large Language Models (LLMs) significantly enhances their long-context capabilities but incurs prohibitive memory costs due to the Key-Value…
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Xiang Hu, Xinyu Wei, Hao Gu +10
Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse atten…
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
Junjie Peng, You Wu, Haoyi Wu +4
Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining the KV cache incurs substan…
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference
You Wu, Ziheng Chen, Yizhen Zhang +6
Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the memory consumption of the KV…
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Xiang Hu, Jiaqi Leng, Jun Zhao +2
A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. H…
A Systematic Study of Compositional Syntactic Transformer Language Models
Yida Zhao, Hao Xve, Xiang Hu +1
Syntactic language models (SLMs) enhance Transformers by incorporating syntactic biases through the modeling of linearized syntactic parse trees alongside surface sentences. This p…