πŸ“– Step 9: AI/LLM#315 / 350

Throughput

Throughput

πŸ“–One-line summary

The number of requests or tokens that can be processed per unit of time.

πŸ’‘Easy explanation

How many requests can be handled per second (or minute). The more users you have, the higher throughput you need.

✨Example

1μ΄ˆμ— λͺ‡ 개 처리?

# μ²˜λ¦¬λŸ‰ λͺ¨λ‹ˆν„°λ§

β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 100 req/s βœ…

β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 250 req/s ⚑

β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 500 req/s πŸ”₯

λ†’μ„μˆ˜λ‘ 더 λ§Žμ€ μ‚¬μš©μž 수용