ORBiS Tree
KO

ORBiS TREE · ENGLISH DOCUMENT

Concepts →

Context Window

The amount of tokenized input and generated text a model can consider within one inference context.

한국어 English
#Attention#Context Window#LLM#Tokenization
Korean source Edit source
English updated 8월 29, 2026 Source article updated 8월 29, 2026 1 sources
This English page is a curated translation layer linked to the Korean source article. Community changes are currently made on the Korean source, where the full revision history and anonymous edit trail are preserved.
A context window is the token budget available to a model for the current interaction. It may include instructions, user messages, retrieved documents, tool outputs, conversation history, and generated tokens.

How it works

Longer context allows more information to be supplied directly, but it increases memory and compute requirements and does not guarantee that every detail will be used equally well. Tokenization means the limit is measured in tokens rather than characters or words.

Why it matters

Context limits influence application design, retrieval strategies, summarization, and cost. Large windows can reduce some retrieval pressure, while RAG remains useful for selecting relevant information from larger corpora.

Related concepts

See also Tokenization, KV Cache, Attention, and Retrieval-Augmented Generation (RAG).

SOURCES

Sources

  1. Llama 2: Open Foundation and Fine-Tuned Chat ModelsMeta AI / arXiv
    Open source ↗

KNOWLEDGE LINKS

Attention → KV Cache → Tokenization →

BACKLINKS

KV Cache Concepts

KEEP EXPLORING

Related articles

Latency and ThroughputTwo core serving metrics describing response delay and the amount of work a system completes over time.GPUA highly parallel processor widely used to train and run modern machine-learning models.InferenceThe process of running a trained model on new input to produce predictions, embeddings, or generated output.Knowledge DistillationA training method in which a smaller student model learns from the outputs or representations of a larger teacher model.QuantizationA technique that represents model weights or activations with lower numerical precision to reduce resource use.Vector SearchSearch that retrieves items by similarity between numerical vector representations.
ORBiS Tree English · source-linked translation
Korean source & revision history · Report an issue · Editorial policy