Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

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 leveraged to reduce the inference cost by converting parts of the
network into equivalent Mixture-of-Experts (MoE) layers. Despite the crucial role
played by activation sparsity, its impact on this process remains unexplored. We
demonstrate that the efficiency of the conversion can be significantly enhanced
by a proper regularization of the activation sparsity of the base model. Moreover,
motivated by the high variance of the number of activated neurons for different
inputs, we introduce a more effective dynamic-k expert selection rule that adjusts
the number of executed experts on a per-token basis. To achieve further savings,
we extend this approach to multi-head attention projections. Finally, we develop an
efficient implementation that translates these computational savings into actual wallclock speedup. The proposed method, Dense to Dynamic-k Mixture-of-Experts
(D2DMoE), outperforms existing approaches on common NLP and vision tasks,
reducing inference cost by up to 60% without significantly impacting performance.