LAION-AI / LAION-AI/Open-Assistant
Load test inference-server on different hardware
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 37.4k
- Forks
- 3.3k
- PR merge metrics
- No merged PRs in 30d
Description
We want to test how many users the inference-server can serve and with what response times on setups with different numbers / types of GPUs & CPUs devices.
On the Stability AI cluster we can perform the load tests with up to 8, 16, 32, 128 pre-emptable GPUs.
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
The issue names the inference-server but no files, tests, or entry points. Start by locating the inference-server and any existing deployment or benchmarking entry points, then establish how hardware configurations and response-time results should be recorded. Done means load-test results cover the proposed GPU and CPU setups and report capacity and response times.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend, machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100