All terms

Inference

Running a trained model on new data to produce predictions or generated output — the "using" phase of ML.

Machine Learning1 min read

Definition

Training teaches a model; inference applies it. When ChatGPT answers your question or a classifier labels an email, that is inference.

Production inference concerns latency, cost, scaling, and reliability — often separate from the research notebook where the model was built.

In simple terms

Training is studying for an exam. Inference is taking the exam — applying what you learned to new questions.

Where you see it

  • API calls to OpenAI are inference.
  • On-device keyboard suggestions run inference locally.
  • Somali ASR transcribing audio in real time.

How it works

  1. 1.Load checkpoint

    Serve trained weights in a runtime (PyTorch, ONNX, vLLM).

  2. 2.Accept input

    Batch requests for efficiency.

  3. 3.Forward pass only

    No backpropagation — faster than training.

  4. 4.Return output

    Text, labels, embeddings, or audio depending on the model.

Why it matters

  • Most users interact with AI at inference time — speed and cost here define product quality.

Often confused

  • Bigger models always infer faster.

    Larger models are usually slower; distillation and quantization trade size for speed.