Ligeng Zhu

Count the MACs / FLOPs of your PyTorch model.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.

My best practice of training large dataset using PyTorch.

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

Sublinear memory optimization for deep learning. https://arxiv.org/abs/1604.06174

On-Device Training Under 256KB Memory [NeurIPS'22]