sgl-project / sgl-project/SpecForge
[Feature] EAGLE3.1 support
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 347
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 41
Description
Checklist
- 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/SpecForge/discussions/new/choose Otherwise, it will be closed.
- 2. Please use English, otherwise it will be closed.
Motivation
Any official plans to support EAGLE 3.1 training? I am currently investigating this and may have some code ready. Will update this post and open a PR later with some results. See: [https://github.com/sgl-project/SpecForge/pull/568]
Links:
Related resources
No response
Contributor guide
No contributing guide indexed for this repository
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
Review the EAGLE 3.1 vLLM blog and TorchSpec PR #97, then inspect the linked SpecForge PR #568 for the proposed training support. Done means establishing the project's EAGLE 3.1 training support and documenting or implementing the agreed result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100