Unverified50% confidenceFactExact time
The prefill phase requires processing all input tokens at once and is a compute-intensive operation, whereas the decode phase generates only one token per step and is a memory-bandwidth-intensive operation.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Prefill phase is a compute-intensive task with high demands on compute power; the Decode phase is a memory-access-intensive task that is sensitive to GPU memory bandwidth.75% similarVerified连续批处理（Continuous Batching）采用迭代级别的调度粒度，每完成一个 token 生成便可移出已完成请求并插入新请求74% similarUnverifiedPrefix Cache optimization refers to the API server's ability to cache the KV computation results of an unchanged system prompt prefix across multi-turn conversations for reuse by subsequent requests, reducing redundant computation and lowering latency and token costs.72% similarUnverifiedDue to the autoregressive nature, each decode step requires accessing the KV Cache of all previous tokens.68% similarUnverifiedvLLM的前缀缓存（Prefix Caching）对KV Cache块计算哈希值，当新请求输入前缀与已缓存请求重叠时直接复用物理缓存块，跳过该部分prefill计算67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972253API
curl https://kongchang.com/api/v1/knowledge/claims/972253MCP
get_claim(id=972253)