the.ai

Inference / Memory

verified

Context Window

A model can only attend to what fits in its context window — the maximum number of tokens it can hold at once. Everything outside is invisible, not merely deprioritised. Extending it is one of the more expensive things to ask for, because attention cost grows with the square of the length and the cache grows linearly with it.

Viz primitive · budget-splittokens-used = 1024

tokens-used holds 48% of the budget; rest holds the remaining 52%.

Tokens of conversation already in the window against the reserve held back for the reply. Drag the usage up to watch the conversation crowd everything else out — what no longer fits is not deprioritised, it is invisible.

1024

Reviewed by opendroid · 2026-08-17

  • arXiv:1901.02860 — Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
  • arXiv:2004.05150 — Longformer: The Long-Document Transformer
  • arXiv:2306.15595 — Extending Context Window of Large Language Models via Positional Interpolation