Unverified50% confidenceFactExact time
The Prefill stage of LLM inference is a compute-intensive operation whose primary bottleneck is GPU/NPU compute (FLOPS).
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLLM 推理分为预填充阶段（Prefill，计算密集型）和解码阶段（Decode，内存带宽密集型）两个阶段79% similarUnverifiedLLM推理的prefill阶段并行处理输入所有token并生成初始KV Cache，是计算密集型操作，是TTFT的直接决定因素76% similarVerifiedIn LLM inference scenarios, GPU memory capacity is often more critical than peak compute performance.73% similarUnverifiedLLM推理的Prefill阶段计算复杂度随上下文长度呈O(n²)增长，是旗舰模型单次请求成本远高于轻量模型的根本原因73% similarUnverifiedThe Prefill stage of autoregressive model inference processes the entire prompt at once, which is a standard GEMM operation with high arithmetic intensity and is compute-bound.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945138API
curl https://kongchang.com/api/v1/knowledge/claims/945138MCP
get_claim(id=945138)