[AutoDeploy]: Multi-stream optimizations for DS-R1
Open
@galagam is already working on this.
Since Dec 10, 2025.
AutoDeploy
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
"There are some small operations which can be run in parallel like the Q norm and KV norm inside the MLA. These operations cannot fully utilize the GPU math flops and the memory bandwidth, thus running in parallel CUDA streams can bring speed-up."
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.