ORBiS Tree

ORBiS TREE · ENGLISH DOCUMENT

Concepts →

Latency and Throughput

Two core serving metrics describing response delay and the amount of work a system completes over time.

한국어 English
English updated 8월 29, 2026 Source article updated 8월 29, 2026 2 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.
Latency measures how long a request or generation step takes, while throughput measures how much work a system completes in a period of time. In AI serving, both matter and often trade off against one another.

How it works

Language-model systems may track time to first token, time per output token, requests per second, or tokens per second. Batching can improve throughput while increasing waiting time, and longer contexts can raise computational and memory costs.

Why it matters

Production systems should measure latency and throughput under realistic traffic, prompt lengths, output lengths, and hardware conditions rather than relying on one isolated benchmark number.

Related concepts

SOURCES

Sources

  1. Open source ↗
  2. Open source ↗