Verified85% confidenceBenchmarkExact time
PagedAttention divides the KV cache into fixed-size pages allocated on demand, and can improve VRAM utilization by 2–4×.
5
Sources
85%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCompared to traditional contiguous allocation, PagedAttention can increase the number of concurrent requests on the same GPU by 2–4 times.77% similarUnverifiedPagedAttention 使显存利用率提升至接近 100%，实现同等硬件下并发吞吐量提升 2-4 倍74% similarVerifiedPagedAttention技术借鉴操作系统虚拟内存的分页思想，将KV Cache切分为固定大小的物理块动态分配73% similarVerifiedPagedAttention improves KV Cache memory utilization from below 40% to close to 100%.73% similarUnverifiedvLLM's PagedAttention splits the KV cache into fixed-size physical blocks (typically 16 tokens), improving GPU memory utilization from below 40% to close to 90%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802147API
curl https://kongchang.com/api/v1/knowledge/claims/802147MCP
get_claim(id=802147)