2 papers
cs.LG2024
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
Bartosz Wójcik, Alessio Devoto, Karol Pustelnik +2
While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a sma…
cs.LG2024
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Filip Szatkowski, Bartosz Wójcik, MikoÅaj PiórczyÅski +1
Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be…