1911.02150

N/A

Fast Transformer Decoding: One Write-Head is All You Need Noam Shazeer Google noam@google.com arXiv:1911.02150v1 [cs.NE] 6 Nov 2019 November 7, 2019…

related reading

• transformer_attention.pdfarxiv.org
• The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• 1706.03762arxiv.org
• Transformer Inference Arithmetic | kipply's blogkipp.ly
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Transformers Inference Optimization Toolset | AstraBlogastralord.github.io
• The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• The Annotated Transformernlp.seas.harvard.edu
• The Annotated Transformernlp.seas.harvard.edu
• Multi Query Attention (MQA) and Grouped-Query Attention (GQA)tinkerd.net
• [2205.14135] FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenessarxiv.org
• 2305.13245arxiv.org