Sparse attention can effectively mitigate the significant memory and
throughput demands of Large Language Models (LLMs) in long contexts. Existing
methods typically employ a uniform sparse attention mask, applying the same
sparse pattern across different attention heads and input lengths. However,
this uniform approach fails to capture the diverse attention patterns inherent
in LLMs, ignoring their distinct accuracy-latency trade-offs. To address this
challenge, we propose the Mixture of Attention (MoA), which automatically
tailors distinct sparse attention configurations to different heads and layers.
MoA constructs and navigates a search space of various attention patterns and
their scaling rules relative to input sequence lengths. It profiles the model,
evaluates potential configurations, and pinpoints the optimal sparse attention
compression plan. MoA adapts to varying input sizes, revealing that some
attention heads expand their focus to accommodate longer sequences, while other
heads consistently concentrate on fixed-length local contexts. Experiments show
that MoA increases the effective context length by $3.9\times$ with the same
average attention span, boosting retrieval accuracy by $1.5-7.1\times$ over the
uniform-attention baseline across Vicuna-7B, Vicuna-13B, and Llama3-8B models.
Moreover, MoA narrows the capability gaps between sparse and dense models,
reducing the maximum relative performance drop from $9\%-36\%$ to within $5\%$
across two long-context understanding benchmarks. MoA achieves a
$1.2-1.4\times$ GPU memory reduction and boosts decode throughput by $5.5-6.7
\times$ for 7B and 13B dense models on a single GPU, with minimal impact on
performance.

稀疏注意力能够有效缓解大型语言模型在长上下文中的内存和吞吐量需求，我们提出了混合注意力（MoA），它能够自动为不同的注意力头部和层级适应不同的稀疏注意力配置，通过优化稀疏注意力压缩方案，MoA 在保持平均注意力范围不变的情况下，将有效上下文长度提高 3.9 倍，并在多个评估指标上取得 1.5-7.1 倍的准确性提升，在 GPU 内存减少 1.2-1.4 倍的同时，提升解码吞吐量 5.5-6.7 倍。