Unverified50% confidenceBenchmarkExact time
PagedAttention causes KV cache memory waste to occur only in the last unfilled block of a request, and vLLM reports waste of less than 4%.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPagedAttention was proposed by the vLLM team in 2023; drawing on the virtual memory paging mechanism of operating systems, it reduced the KV Cache memory waste rate from over 60% to close to 4%.74% similarVerifiedvLLM's PagedAttention draws on the operating system concept of virtual memory paging to manage KV caches, reducing GPU memory fragmentation overhead from approximately 30% to near 0.72% similarUnverified传统LLM推理中，KV Cache的内存管理导致60%-80%的GPU显存被浪费70% similarVerifiedPagedAttention improves KV Cache memory utilization from below 40% to close to 100%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006018API
curl https://kongchang.com/api/v1/knowledge/claims/1006018MCP
get_claim(id=1006018)