Removed: Large Language Models on Mobile Devices: Measurements, Analysis, and Insights
Removed: PowerInfer-2: Fast Large Language Model Inference on a Smartphone
Removed: Empowering 1000 tokens/second on-device LLM prefilling with mllm-NPU
Removed: Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference
Removed: Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference
Removed: Large Language Models on Mobile Devices: A Measurement Study of Single- and Multi-Instance Execution