Inference and deployment
Speculative Decoding
An inference method in which a faster draft proposes multiple tokens and the target model verifies them in parallel. It can reduce generation latency without changing the target distribution.
Key terms
- draft model
- verification
- latency
- exact sampling
Connected across the project
Builds on
Used by
Related technology
Related papers
Historical context
Primary sources
This is a curated technical map, not a claim of comprehensive coverage.