ML System

• MCUNet: Tiny Deep Learning on IoT Devices
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
• TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
• A systematic methodology for analysis of deep learning hardware and software platforms
• Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators
• A Learned Performance Model for Tensor Processing Units
• Learned TPU Cost Model for XLA Tensor Programs
• Efficient Mixed-Precision Large Language Model Inference with TurboMind