cs 3

• [Paper Reproducing] llm.npu Reproducing on Snapdragon 8 elite Sep 2, 2025
• [Paper Review] Fast On-device LLM Inference with NPUs Aug 9, 2025
• [Paper Review] HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs with Heterogeneous AI Accelerators Aug 2, 2025