Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Adaptive Discretization for Consistency Models
Jiayu Bai, Zhanbo Feng, Zhijie Deng +3
Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated…
cs.LG2024
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
Bokai Lin, Zihao Zeng, Zipeng Xiao +5
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) a…