Systems and efficient execution · MLD-0724
Memory bandwidth
The rate at which data can be transferred to or from a memory system.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Analyze a memory-bound inference workload.
Original caveat
Peak hardware bandwidth is not necessarily achieved in practice.
Context and aliases
Level: Advanced. 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 ↗