Unverified50% confidenceFactExact time
When sequence length n grows from 2K to 128K, the attention computation volume increases approximately 4,000-fold.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe context window of modern large models has expanded from the early 4K tokens to 128K or even longer, and the computational complexity of the attention mechanism grows quadratically with context length.80% similarUnverifiedFrom a resolution increase of 1.0mp to 2.5mp, the time cost growth typically far exceeds 2.5×, because the computational complexity of self-attention is proportional to the square of the number of tokens.79% similarUnverifiedThe computational complexity and memory consumption of the self-attention mechanism are both O(n²); when the input increases from 1K to 10K tokens, the amount of computation increases approximately 100-fold79% similarUnverifiedWhen the context expands from 4K tokens to 128K tokens (a 32× increase), the theoretical computation grows by approximately 1024×.74% similarUnverified将上下文从128K扩展到1M，理论计算量会增加约60倍72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990366API
curl https://kongchang.com/api/v1/knowledge/claims/990366MCP
get_claim(id=990366)