[AutoDeploy] BTK findings: Nano doesn't scale well for tp>1
Open
@MrGeva is already working on this.
Since May 11, 2026.
AutoDeploy
feature request
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
Nano output TPS for tp=1 ~ TPS for tp=2,4,8 - no scaling at all.
This is true for both FP8 and NVFP4 variants.
Super is able to scale well on B200. See #11393 .
Suspecting host-boundness due to host-side inefficiencies.
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.