Verified75% confidenceFactExact time
P/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).
3
Sources
75%
Confidence
Long-term
Relevance
9/11/2026
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% similarUnverifiedTransformer inference is divided into two stages, prefill and decode: prefill processes the entire input prompt in parallel at once and is mainly compute-bound; decode generates output tokens one by one and is mainly memory-bandwidth-bound.77% similarUnverifiedThe Disaggregated Inference architecture assigns the Prefill and Decode stages to different hardware instances for execution.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74% similarVerifiedThe decode phase is a memory-bandwidth-intensive operation, and overall throughput is constrained by VRAM bandwidth rather than compute.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908699API
curl https://kongchang.com/api/v1/knowledge/claims/908699MCP
get_claim(id=908699)