168 citations · 398 across the 15 of their papers we have counts for
7 papers · 1 filter
New Solutions on LLM Acceleration, Optimization, and Application
Yingbing Huang, Lily Jiaxin Wan, Hanchen Ye +5
Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. H…
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Tianle Cai, Yuhong Li, Zhengyang Geng +4
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as…
Extensible Proxy for Efficient NAS
Yuhong Li, Jiajie Li, Cong Han +3
Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are fur…
What Makes Convolutional Models Great on Long Sequence Modeling?
Yuhong Li, Tianle Cai, Yi Zhang +2
Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle long-range dependency ef…
Compilation and Optimizations for Efficient Machine Learning on Embedded Systems
Xiaofan Zhang, Yao Chen, Cong Hao +3
Deep Neural Networks (DNNs) have achieved great success in a variety of machine learning (ML) applications, delivering high-quality inferencing solutions in computer vision, natura…
Generic Neural Architecture Search via Regression
Yuhong Li, Cong Hao, Pan Li +2
Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive…
EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions
Yuhong Li, Cong Hao, Xiaofan Zhang +5
High quality AI solutions require joint optimization of AI algorithms and their hardware implementations. In this work, we are the first to propose a fully simultaneous, efficient…