sgl-project / sgl-project/SpecForge
[Feature] TTT implementation is not the original paper’s concept, but merely data augmentation
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
Thanks to the SpecForge team for their enthusiastic open-sourcing. But after carefully reading through all the core implementations, I found that:
-
According to the original principle of EAGLE-style, it seems that this should be "left=True".
-
TTT implementation is not the original EAGLE-3 paper’s concept, but merely data augmentation. Please refer to the details here.
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
Start with the linked sections of specforge/core/eagle3.py, especially the left=True setting and the TTT implementation around lines 398-439. Compare those paths with the original EAGLE-3 paper and the referenced SafeAILab discussion; done means the implementation reflects the paper’s concept rather than only data augmentation.
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
- Mostly clear
- Newbie friendliness
- 28/100