Skip to main content

Module inference

Module inference 

Source
Expand description

Basic inference implementation Complete inference pipeline for text generation

This module ties together tokenization, model inference, and text generation into a complete pipeline that can process text input and generate responses.

Structsยง

InferenceMetrics
Performance metrics for inference
InferencePipeline
Complete inference pipeline
InferencePipelineBuilder
Builder for creating inference pipelines
Sampler
Sampling strategy for text generation