Support Speculative Decoding
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 537
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
This could be used for LLMs and hopefully for encoder-decoder models like using the smaller NLLB coupled with the bigger NLLB models
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points, so begin by locating the model inference and decoding components relevant to CTranslate2. Done would mean speculative decoding support for LLMs, with encoder-decoder support such as pairing smaller and larger NLLB models clarified or explicitly scoped.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100