Unverified50% confidenceFactExact time
Time per output token (TPOT) measures the speed at which a model generates tokens one by one during the autoregressive decoding phase.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAutoregressive generation refers to the model predicting the next token each time based on all previously generated tokens, progressively unfolding until a complete code block is generated67% similarUnverifiedLarge language models use an autoregressive generation mechanism, sampling the next token at each step based solely on a probability distribution, with each token's generation conditioned on all preceding tokens to form a chain of probabilistic dependencies.64% similarUnverified在二分类问题中召回率（Recall/Sensitivity）计算公式为TP/(TP+FN)，衡量模型识别所有真实阳性样本的能力64% similarUnverifiedLLM自回归解码阶段每生成一个token都需从显存加载全量模型权重，批量较小时形成内存墙63% 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63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/831543API
curl https://kongchang.com/api/v1/knowledge/claims/831543MCP
get_claim(id=831543)