๐ Step 9: AI/LLM#310 / 350
Inference
Inference
๐One-line summary
The process where a trained model generates output for new input.
๐กEasy explanation
The process of a trained model actually answering questions. If training is 'studying,' inference is 'taking the test.' It happens every time you call an API.
โจExample
ํ์ต = ๊ณต๋ถ ยท ์ถ๋ก = ์ํ
๐
Training
์๊ฐ์ ยท ๊ณ ๋น์ฉ
GPU ์์ฒ ๊ฐ
โ๏ธ
Inference
๋ฐ๋ฆฌ์ด ๋จ์
API ํธ์ถ๋ง๋ค ์คํ