Unverified50% confidenceFactExact time
In generative large models, a single forward pass usually produces only one token, and to obtain a complete output the result must be fed back into the input and called repeatedly, i.e., autoregressive decoding.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大模型推理的自回归生成需要逐Token串行输出，生成N个Token需要N次前向传播79% similarUnverifiedFor each token generated or processed, one forward pass must be executed, and its computational cost is roughly proportional to the number of model parameters.78% similarVerifiedThe token generation process of large language models is serial, based on an autoregressive mechanism, where each token's generation depends on the previous token.77% similarUnverifiedThe autoregressive generation mode means the model must generate tokens one by one and cannot output an entire response in parallel.77% similarUnverifiedDuring Transformer model inference, input tokens can be processed in parallel (prefill stage), while output tokens must be generated one by one autoregressively (decode stage), causing the unit price of output tokens to typically be higher than that of input tokens.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074389API
curl https://kongchang.com/api/v1/knowledge/claims/1074389MCP
get_claim(id=1074389)