From the 1 of 14 linked papers with an AI index.
14 papers
Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding
Weiye Shi, Fanxu Meng, Muhan Zhang
The paper proposes a functional reconstruction method to convert multi-head or grouped-query attention models into multi-head latent attention form, preserving cache efficiency and…
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
Yansheng Mao, Yufei Xu, Jiaqi Li +5
Long-context understanding remains challenging for LLMs due to limited context windows. This paper introduces Long Input Fine-Tuning (LIFT), a framework that improves the long-cont…
GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding
Fanxu Meng
Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. I…
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
Ruijie Zhou, Fanxu Meng, Yufei Xu +4
DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix toke…
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
Yufei Xu, Fanxu Meng, Fan Jiang +11
Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a…
Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation
Pingzhi Tang, Ruijie Zhou, Fanxu Meng +2
Current quantization methods for LLMs predominantly rely on block-wise structures to maintain efficiency, often at the cost of representational flexibility. In this work, we demons…