I am a fifth-year Ph.D. student in the CS department of Georgia Tech, who is passionate about efficient/automated ML and algorithm-hardware co-design!
Github Stats | Streak Stats |
---|---|
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
[ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
[ICLR 2020] Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks
[HPCA 2023] ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
[NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
Python 31
[CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference