Showing 2025Show all
2 papers · 1 filter
cs.AR2025
CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference
Yanru Chen, Runyang Tian, Yue Pan +3
The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency an…
cs.AR2025
SLIM: A Heterogeneous Accelerator for Edge Inference of Sparse Large Language Model via Adaptive Thresholding
Weihong Xu, Haein Choi, Po-kai Hsu +2
Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devi…