[Feature]: Investigate the unstable perf of llama 3.1 8B fp8 in CI test_sanity_perf.py
Open
Nobody has claimed this yet.
feature request
General perf
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
Investigate why llama 3.1 8B fp8 provides unstable results across CI runs and cannot be tested in CI. see:
https://nvbugspro.nvidia.com/bug/6244474
This model is host bound (even in c=256) so the fluctuation is most likely related to cpu load.
Alternatives
No response
Additional context
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.
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.
Assessment
This issue has not been assessed yet.