Unverified50% confidenceFactExact time
The prefill phase performs one forward computation over the entire input to produce KV caches for all positions, and is compute-bound; the decode phase generates tokens autoregressively one by one and is memory-bandwidth-bound.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe Prefill phase is a compute-intensive operation, while the Decode phase is a memory-bandwidth-intensive operation.79% similarUnverifiedAt the hardware level, the Prefill (input) stage can read all tokens in parallel and compute the self-attention matrix simultaneously, whereas the Decode (output) stage requires serial autoregressive token-by-token inference, causing GPU utilization to drop sharply.77% similarUnverified输入Token可以在prefill阶段并行处理，而输出Token必须在decode阶段逐个串行生成76% similarUnverified输出Token定价高于输入Token是因为Prefill阶段可并行矩阵运算而Decode阶段必须串行自回归解码，Decode阶段GPU吞吐量约为Prefill阶段的1/6到1/1075% similarUnverifiedPrompt caching technology stores KV matrices in high-speed memory, and when the next request contains the same prefix content, it reads directly from the cache, skipping recomputation.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070061API
curl https://kongchang.com/api/v1/knowledge/claims/1070061MCP
get_claim(id=1070061)