sgl-project / sgl-project/SpecForge
Support for target and draft models on different GPUs
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 347
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 41
Description
Hi there,
Thanks for your work on SpecForge. Does it support running the target model and draft model on different GPUs (e.g., GPU 0 and GPU 1) or across different machines?
Best regards
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
No files, tests, or entry points are named in the issue. First determine whether SpecForge currently supports placing target and draft models on separate GPUs or machines, then identify the relevant execution and configuration paths. Done means the supported deployment behavior is documented or implemented and verified for the requested arrangements.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100