4 papers · 1 filter
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
Sihao Liu, YuFan Xiong, Zhonghua Jiang +2
Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing l…
MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?
Xingze Zou, Jing Wang, Yuhua Zheng +8
Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet their potential for generating kernels specifically for mobile devices remains largel…
MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices
Zhaode Wang, Jingbang Yang, Xinyu Qian +4
Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consu…
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
Kunxi Li, Zhonghua Jiang, Zhouzhou Shen +5
This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-cont…