mlcommons / mlcommons/inference
Add github actions to test the accuracy scripts of LLM models
Open
Nobody has claimed this yet.
tests
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 650
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 6
Description
We currently do not have github actions for LLM benchmarks due to the long runtimes. But we can at least add github actions to test the accuracy scripts using pregenerated accuracy logs.
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
No files or tests are named. Start by locating the LLM accuracy scripts and their pregenerated accuracy logs, then inspect the repository's existing GitHub Actions workflows. Done means a workflow runs the accuracy scripts against the pregenerated logs without requiring the long benchmark runs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- github-actions, python
- Domain
- ci-cd, machine-learning, testing-qa
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100