Unverified50% confidenceFactExact time
Prefilling refers to when, in using a large language model API, the caller pre-provides a piece of text (or token sequence) for the model to continue generating from, rather than starting from an empty context.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrefill is the first stage of large language model inference, in which the model reads the entire prompt entered by the user in one pass and computes key-value vectors for each token and stores them in VRAM.76% similarUnverified语言模型生成 token 本质上是内存带宽受限任务而非纯算力受限66% similarVerifiedThe Prefill phase is a compute-intensive operation, while the Decode phase is a memory-bandwidth-intensive operation.66% similarUnverifiedPrefixLM (prefix language model) is an architecture design between autoencoding (such as BERT) and autoregressive (such as GPT): the input sequence is divided into a prefix part and a suffix part, tokens within the prefix part can see each other (bidirectional attention), and the suffix part can only see itself and preceding tokens (causal attention).65% similarUnverifiedExpression evaluation mode means the software first parses the entire line of a mathematical expression into a syntax tree and then evaluates it as a whole, rather than settling immediately each time an operator is pressed.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1103221API
curl https://kongchang.com/api/v1/knowledge/claims/1103221MCP
get_claim(id=1103221)