no code implementations • 5 Dec 2023 • Hengrui Zhang, August Ning, Rohan Prabhakar, David Wentzlaff
With the large hardware needed to simply run LLM inference, evaluating different hardware designs becomes a new bottleneck.
no code implementations • 21 Oct 2021 • Yuchen Liu, S. Y. Kung, David Wentzlaff
While most prior works in evolutionary learning aim at directly searching the structure of a network, few attempts have been made on another promising track, channel pruning, which recently has made major headway in designing efficient deep learning models.
no code implementations • 21 Oct 2021 • Yuchen Liu, David Wentzlaff, S. Y. Kung
We then propose a novel layer-adaptive hierarchical pruning approach, where we use a coarse class discrimination scheme for early layers and a fine one for later layers.
no code implementations • 29 Apr 2020 • Yuchen Liu, David Wentzlaff, S. Y. Kung
To this end, we initiate the first study on the effectiveness of a broad range of discriminant functions on channel pruning.