4 papers
CacheBridge: Efficient Cross-Model KV Cache Transfer
Xingyu Qu, Siyuan Lu, Zhiyu Chen +2
Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Recent closed-form cross-model…
Can Muon Fine-tune Adam-Pretrained Models?
Xingyu Qu, Peigeng Huang, Samuel Horvath
Muon has emerged as an efficient alternative to Adam for pretraining, yet remains underused for fine-tuning. A key obstacle is that most open models are pretrained with Adam, and n…
PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design
Xingyu Qu, Tianhao Lin, Yiqi Li +2
Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segment…
Vanishing Feature: Diagnosing Model Merging and Beyond
Xingyu Qu, Samuel Horvath
Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initiali…