[feature request] Support multiple rollout worker for CPU-heavy custom `generate` function
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 1.3k
- Avg merge
- 5h 36m
- Merged PRs (30d)
- 22
Description
For some tool-call or complex agent scenario, the custom generate function is CPU heavy. it would be better to share the CPU load across nodes.
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
Start by locating the rollout worker and the custom generate entry point in the Python repository. Clarify how CPU-heavy generation should be shared across nodes and what support for multiple workers should look like; done means the requested multi-worker rollout behavior is implemented and verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, distributed-systems
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100