Missing possibility for GET request against model_workers for "liveness" and "readiness" signals for kubernetes
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
Its a bit weird that there is no possibilities for a GET in the endpoints on the model workers.
I would think the worker_get_status would be a prime opportunity:
https://github.com/lm-sys/FastChat/blob/e4758da20dae96486fceb0cce24e5107c4cfc2eb/fastchat/serve/model_worker.py#L443
Our reason for needing this is deploying to kubernetes where it requires some get-endpoints to check if the app is running correctly. Etc "liveness".
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 in fastchat/serve/model_worker.py around worker_get_status and inspect the model-worker endpoints. Determine the response needed for Kubernetes liveness and readiness probes. Done means the model worker exposes usable GET endpoint behavior for those checks and the endpoint can be verified against the stated Kubernetes deployment need.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes, python
- Domain
- api, devops
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100