deepseek-ai / deepseek-ai/DeepEP
deep_ep::intranode::cached_notify_combine<8> takes very long
Open
- Dominant language
- Cuda
- Stars
- 10.1k
- Forks
- 1.4k
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 2
Description
Hi team,
I'm doing intronode EP with deepep. But cached_notify_combine() could takes 13-23ms, while the grouped gemm only taks less than 3ms. Do you have any insight about potential reasons?
deep_ep::intranode::combine() takes 7ms or less.
deep_ep::intranode::dispatch() takes around 5ms.
Thanks a lot!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.