Decoding and inference behavior · MLD-0339
Draft model
A cheaper model proposing tokens for speculative decoding.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Suggest several future tokens before target verification.
Original caveat
A larger or more accurate draft is not always faster overall.
Context and aliases
Level: Intermediate. Stages: Inference · Evaluation · Deployment.
Tags: SLM · LLM · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Hugging Face: generation strategies ↗ · Reference link
- Fast Inference from Transformers via Speculative Decoding ↗ · Consulted
- vLLM documentation ↗ · Consulted
- Original reference URL ↗