2 papers
cs.LG2026
MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs
Zile Wang, Zhide Xie, Tao Ji
Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth. Existing MHA2MLA/TransMLA methods do not support QK…
cs.CL2026
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
Zile Wang, Qianli Liu, Kaibin Guo +4
Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized agents presents a unique opp…