mlcommons / mlcommons/endpoints
Perf: Analayze the roofline of the inference endpoints
Open
Nobody has claimed this yet.
area: core-engine
priority: P1
type: performance
- Dominant language
- Python
- Stars
- 21
- Forks
- 28
- Avg merge
- 3d 17h
- Merged PRs (30d)
- 13
Description
We need to understand the roofline of:
- In offline, the maximum number of queries/reponses we can handle each second
- In online (concurrency), the maximum concurrency that we can measure for the endpoints
- In online, the maximum SSE chunks we can stream each second (which will impact our TPS roofline)
We can use SemiAnalsysis data as a reference: https://inferencemax.ai/
This will prepare us for the future when we need to horizontally scale to measure endpoints served on a larger cluster
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 no files, tests, or entry points; begin by locating the offline and online inference endpoint benchmarks and review the SemiAnalysis reference. Done means documenting reproducible limits for queries/responses per second, concurrency, and SSE chunks per second, with enough measurement context to guide horizontal scaling.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend-api-design, machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100