huggingface / huggingface/lighteval
[FT] LiteLLM concurrency parameters hard-coded
Open
feature
good first issue
help wanted
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 555
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 1
Description
I noticed that for LiteLLM the concurrency is hard-coded for an arbitrary number (20). Well, a lot of the request behavior is hard coded, but the concurrency is the one that is probably least likely to work well as a one size fits all.
If everything is going through the YAML file, maybe it can be expanded, although the YAML file is another ball of wax (makes automated runs much harder when you can't just pass in parameters via a call)
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.