Systems and efficient execution · MLD-0096
Batch inference
Producing predictions for a collection of inputs, often without an interactive response deadline.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Score a large document archive overnight.
Original caveat
Batch processing can also occur inside real-time serving.
Context and aliases
Level: Advanced. Stages: Training · Inference · Deployment.
Tags: DL · LLM · SLM · Systems.
Aliases: Batch prediction.
Related concepts
Concepts linking here
Original references
- PyTorch Fully Sharded Data Parallel ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- vLLM documentation ↗ · Consulted
- Original reference URL ↗