Transformer Architecture · 2020

GLU Variants Improve Transformer (SwiGLU)

Noam Shazeer

Showed that replacing the transformer feed-forward layer's ReLU with gated linear unit variants, especially SwiGLU, yields better quality at matched compute.

Editorial record

Plain-language summary

The paper swaps the standard two-matrix ReLU feed-forward block for GLU variants, where one linear projection is elementwise-multiplied by a gated (sigmoid, GELU, or Swish) version of another projection. In controlled pretraining and fine-tuning comparisons, these gated blocks lower perplexity and improve downstream scores over the plain ReLU feed-forward. SwiGLU became the standard feed-forward design in PaLM, LLaMA, and most subsequent large models.

Knowledge graph

Relationships

Descendants

Source record

Provenance

Record ID
P-004
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.