InferenceSequence<T, TInput, TOutput>
Models & Types · AiDotNet.Models.Results
Represents one independent, stateful inference sequence (e.g., one chat/generation stream).
Implements: IDisposable
How It Works
A sequence may keep internal state across calls when inference optimizations are enabled (e.g., KV-cache).
Call Reset to start a new logical sequence on the same object.
Methods
| Method | Summary |
|---|---|
TOutput Predict(TInput newData) |
Runs a prediction for the given input within this sequence. |
void Dispose() |
|
void Reset() |
Resets sequence-local inference state. |