10 papers
LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization
Zexun Lin, Yuan Feng, Junlin Lv +2
Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically determined by the speculative leng…
AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
Dinghong Song, Yuan Feng, Yiwei Wang +6
Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification,…
Taming the Fragility of KV Cache Eviction in LLM Inference
Yuan Feng, Haoyu Guo, JunLin Lv +2
Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key…
Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
Yuan Feng, Yukun Cao, Hairu Wang +2
Sketches, probabilistic structures for estimating item frequencies in infinite data streams with limited space, are widely used across various domains. Recent studies have shifted…
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context
Hairu Wang, Yuan Feng, Yukun Cao +2
Large language models excel at many tasks but often incur high inference costs during deployment. To mitigate hallucination, many systems use a knowledge graph to enhance retrieval…
Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
Hairu Wang, Yuan Feng, Xike Xie +1
Although Large Language Models achieve strong success in many tasks, they still suffer from hallucinations and knowledge deficiencies in real-world applications. Many knowledge gra…
CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
Yuan Feng, Junlin Lv, Haoyu Guo +3
Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the transformer architecture's relia…
FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
Zengyi Gao, Yukun Cao, Hairu Wang +4
To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potentia…
CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs
Junlin Lv, Yuan Feng, Xike Xie +3
Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechan…
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Yuan Feng, Junlin Lv, Yukun Cao +2
Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts a…