Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Curriculum Sampling: A Two-Phase Curriculum for Efficient Training of Flow Matching
Pengwei Sun
Timestep sampling is a central design choice in Flow Matching models, yet common practice increasingly favors static middle-biased distributions (e.g., Logit-Normal). We sho…
cs.LG2025
Semantic-Aware Scheduling for GPU Clusters with Large Language Models
Zerui Wang, Qinghao Hu, Ana Klimovic +4
Deep learning (DL) schedulers are pivotal in optimizing resource allocation in GPU clusters, but operate with a critical limitation: they are largely blind to the semantic context…
cs.LG2025
Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
Wei Gao, Xinyu Zhou, Peng Sun +2
Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory cons…