Systems and efficient execution · MLD-1232
Throughput
The amount of work completed per unit time under a defined workload.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Count generated tokens per second across a server.
Original caveat
Aggregate throughput is not the same as one user's generation speed.
Context and aliases
Level: Foundational. Stages: Training · Inference · Deployment.
Tags: DL · LLM · SLM · Systems.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- PyTorch Fully Sharded Data Parallel ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- vLLM documentation ↗ · Consulted
- Original reference URL ↗