[Feature]: AutoDeploy: fused MoE representation in AutoDeploy IR
Open
@tcherckez-nvidia is already working on this.
Since Feb 10, 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
Move torch_moe to a fused weight representation to reduce export time. Some data points:
Qwen3Next with 512 experts and 48 layers;
~8min
Qwen3Next with 16 experts and 48 layers (simulating fused experts:
16sec
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.