Unverified70% confidenceFactTime unknown
Sliding Window Attention reduces the standard Transformer's O(n²) complexity to O(n·w), but the model cannot directly see information outside the window.
2
Sources
70%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified滑动窗口注意力（如Mistral采用的方案）通过限制每个token只关注固定窗口内的历史，将复杂度从O(n²)降至O(n·w)82% similarUnverifiedSliding window attention is a local attention variant in the Transformer architecture, where each token only attends to tokens within a fixed-length window before and after it, reducing the attention computation complexity from O(n²) to O(n·w).80% similarVerifiedSliding window attention reduces the complexity of attention computation from O(n²) to O(n·w), linearizing GPU memory overhead for long texts.78% similarVerifiedThe self-attention mechanism of the standard Transformer architecture has a computational complexity of O(n²).76% similarUnverified滑动窗口注意力将计算复杂度从O(n²)降至O(n×w)，是Mistral模型家族的核心创新之一75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13915API
curl https://kongchang.com/api/v1/knowledge/claims/13915MCP
get_claim(id=13915)