Unverified50% confidenceFactExact time
Prompt Cache operates on the computation of the Prefill phase, eliminating redundant prefix computation, but cannot skip the generation in the Decode phase.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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72% similarUnverifiedP/D Disaggregation (Prefill/Decode Disaggregation) deploys the Prefill and Decode stages on different nodes to independently scale according to their respective computational characteristics, while simultaneously optimizing throughput and time to first token (TTFT).72% similarVerifiedThe Prefill phase is a compute-intensive operation, while the Decode phase is a memory-bandwidth-intensive operation.71% similarUnverifiedPrefix caching improves inference efficiency by caching common prompt prefixes to reduce redundant computation.70% similarUnverifiedLLM inference requests are divided into two phases—Prefill (input) and Decode (output); Prefill can read inputs in parallel with extremely high throughput, while Decode requires token-by-token serial inference and occupies significantly more GPU time.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908130API
curl https://kongchang.com/api/v1/knowledge/claims/908130MCP
get_claim(id=908130)