Fast Transformer Decoding: One Write-Head is All You Need

作者： Noam Shazeer (2019)

arXiv： 1911.02150

领域

推理架构

TLDR（中文）

提出 Multi-Query Attention：所有 head 共享同一份 K/V，把 KV cache 占用打到 1/h。今天 KV cache 优化、长上下文推理的故事都从这篇 5 页短文开始。

TLDR (English)

Proposes Multi-Query Attention: all heads share the same K/V, reducing KV cache usage to 1/h. All modern KV cache optimization and long-context inference stories start from this 5-page paper.

出现在这些文章里

• 高效注意力：突破序列长度平方瓶颈
• Efficient Attention: Breaking the Quadratic Sequence Bottleneck

同被引用

这些论文与本文出现在同一篇文章中

• GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints Joshua Ainslie et al. (2023)
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness Tri Dao et al. (2022)
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning Tri Dao (2023)
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model DeepSeek-AI (2024)

相关论文

同一领域的其他论文

• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model DeepSeek-AI (2024)
  架构推理
• DeepSeek-V3 Technical Report DeepSeek-AI (2024)
  架构混合专家
• Mixtral of Experts Albert Q. Jiang et al. (2024)
  混合专家架构
• FlashAttention-3: Fast and Accurate Attention with Asympotic IO Complexity Jay Shah et al. (2024)
  推理
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Charlie Snell et al. (2024)
  推理能力推理
• GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints Joshua Ainslie et al. (2023)
  推理架构