lightseekorg/TorchSpec
A PyTorch native library for training speculative decoding models
Is lightseekorg/TorchSpec beginner-friendly?
We have not seen enough recent pull requests from outside contributors to lightseekorg/TorchSpec to say how often they are merged. No beginner-friendly issue is open right now; the list below has the other issues we hold for it.
- Stars
- 266
- Forks
- 69
- Open beginner issues
- 0
- Indexed issues
- 8
- Avg merge
- 1d 1h
- Merged PRs (30d)
- 3
- Dominant language
- Python
- License
- MIT
- Last GitHub push
- Oct 29, 2026
- Latest indexed
- Sep 20, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
How to contribute to lightseekorg/TorchSpec
- Read the contributing guide first: it says how the maintainers want changes proposed, tested and reviewed.
- Your contributions will be published under the project's MIT license.
- Follow the repository to hear when a new beginner-friendly issue opens, or look through the other issues below.
Issues somebody may already be working on are listed last. List everything by date
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
lightseekorg/TorchSpec#209 ·
-
Difficulty 3/5 Half a day Newbie friendliness 62/100
lightseekorg/TorchSpec#208 ·
-
build_rotary_embedding crashes with TypeError on a YaRN rope_scaling that omits beta_fast/beta_slowOpen
Difficulty 3/5 Half a day Newbie friendliness 75/100
lightseekorg/TorchSpec#207 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
lightseekorg/TorchSpec#206 ·
-
Difficulty 3/5 Half a day Newbie friendliness 62/100
lightseekorg/TorchSpec#205 ·
-
SMG binding silently rounds integers outside the i64/u64 range in tool-call arguments to floatsOpen
Difficulty 4/5 3-5 days Newbie friendliness 35/100
lightseekorg/TorchSpec#204 ·
-
Development Roadmap (2026 Q4)May be free again @yubofredwang claimed this 54 days ago, and no pull request is open. Openhigh priority
lightseekorg/TorchSpec#194 · 6 reactions · 2 assignees ·