2 papers
cs.DC2026
HeteroMosaic: Exposing and Exploiting Heterogeneous Execution Opportunities for Energy-Efficient Edge LLM Inference
Gregory Hyegang Jun, Wesley Pang, Eddie Richter +4
Modern edge system-on-chips (SoCs) combine CPUs, integrated GPUs (iGPUs), and neural processing units (NPUs), yet existing LLM runtimes typically make coarse device-level decisions…
cs.DC2026
TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs
Wesley Pang, Gregory Hyegang Jun, Feiyang Liu +1
With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. Howev…