20 citations · 20 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.DC2026
Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling
Cunchen Hu, Liangliang Xu, Tian Liu +9
Large language model (LLM) serving spans diverse applications with stringent service-level objectives (SLOs), often requiring GPUs to run at maximum frequencies and increasing ener…
cs.CL2026
A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding
Yuesong Liu, Yuan Zeng, Min Lyu +3
Speculative decoding alleviates the memory-bandwidth bottleneck in large language model inference, but its acceleration is jointly constrained by drafting overhead, token acceptanc…