1 citations · 1 across the 4 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
Xiaolin Lin, Jingcun Wang, Olga Kondrateva +3
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on…
cs.AI2023
Class-Aware Pruning for Efficient Neural Networks
Mengnan Jiang, Jingcun Wang, Amro Eldebiky +4
Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for thei…