PrototypeCommon
romsto/Speculative-Decoding
Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.
- Owner
- romsto (personal account)
- Stars
- Stars: 116
- Forks
- Forks: 25
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- fast-inferencellmllm-inferencellm-optimizationspeculative-decoding
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- abigailmaria/RoughFeelStars: 116PythonPrototype
- arby18/DraftSenseStars: 116PythonPrototype
- flemuh/radar-public-sectorStars: 116PythonPrototype
- jezdez/django-mobileadminStars: 116PythonPrototype
- montylounge/django-sugarStars: 116PythonPrototype
- codysoyland/django-template-replStars: 116PythonPrototype