Systems and efficient execution · MLD-0285
Decode phase
The inference phase that repeatedly computes new output tokens using the existing context and cached state.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Stream a language-model response token by token.
Original caveat
Decoding speed depends on batching, memory traffic, and architecture.
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 ↗