Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
Dan Peng, Zhihui Fu, Zewen Ye +2
Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attentio…
cs.LG2024
PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
Dan Peng, Zhihui Fu, Jun Wang
Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily…