arXiv:2111.12763cs.LG
Sparse is Enough in Scaling Transformers
Abstract
Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study sparse variants for all layers in the Transformer and propose Scaling Transformers, a family of next generation Transformer models that use sparse layers to scale efficiently and perform unbatched decoding much faster than the standard Transformer as we scale up the model size. Surprisingly, the sparse layers are enough to obtain the same perplexity as the standard Transformer with the same number of parameters. We also integrate with prior sparsity approaches to attention and enable fast inference on long sequences even with limited memory. This results in performance competitive to the state-of-the-art on long text summarization.
I'm pretty sure in GPT3.5+ models, this concept of attention holds no longer true. In [1] the author suggests they are using "Intra-tensor sparsity" from a 2021 paper from Google [2]. Details aside, math suggests they _must_ be using some sparse attention method: the memory used…
spiView on HNParent context