Unverified50% confidenceFactExact time
vLLM's PagedAttention mechanism divides the KV cache into blocks of a fixed number of tokens (usually 16), and records the mapping from logical positions to physical blocks through a block table.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPagedAttention divides the KV Cache into fixed-size blocks, allocates them dynamically on demand, and allows blocks from different requests to be stored non-contiguously.77% similarUnverifiedKV Cache（键值缓存）用于避免自回归生成时对历史 token 的重复计算，但长上下文场景下预填充阶段需占用大量 HBM 显存带宽，拉长首 token 延迟（TTFT）72% similarUnverifiedvLLM引入PagedAttention技术将KV Cache分割为固定大小物理块按需分配，而llama.cpp采用预分配策略在模型加载时一次性保留完整KV Cache空间72% similarUnverifiedThe tiered cache system in vLLM is commonly referred to as Tiered KV Cache and can span multiple storage tiers including GPU HBM, CPU DRAM, NVMe SSD, or remote distributed caches.72% similarVerifiedKV Cache avoids redundant computation by caching already-computed Key and Value matrices, and advanced techniques such as PagedAttention further optimize cache memory management efficiency.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017341API
curl https://kongchang.com/api/v1/knowledge/claims/1017341MCP
get_claim(id=1017341)