3 citations · 3 across the 9 of their papers we have counts for
7 papers · 1 filter
AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
Yuxuan Hu, Jianchao Tan, Jiaqi Zhang +7
Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accur…
TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL
Jinbo Su, Yuxuan Hu, Cuiping Li +4
In Text-to-SQL tasks, existing LLM-based methods often include extensive database schemas in prompts, leading to long context lengths and increased prefilling latency. While user q…
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
Yuxuan Hu, Jianchao Tan, Jiaqi Zhang +7
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternat…
LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model
Yuxuan Hu, Jing Zhang, Xiaodong Chen +3
Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that m…
SAM Decoding: Speculative Decoding via Suffix Automaton
Yuxuan Hu, Ke Wang, Xiaokang Zhang +4
Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have y…
Streamlining Redundant Layers to Compress Large Language Models
Xiaodong Chen, Yuxuan Hu, Jing Zhang +3
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on…
: Enhancing Structured Pruning via PCA Projection
Yuxuan Hu, Jing Zhang, Zhe Zhao +4
Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidde…