Skip to content

GitLab

Commit e130cc6e authored by Chenggang Zhao's avatar Chenggang Zhao
Browse files

Remove NVLink low-latency plan

parent cbd92fd0
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
README.md
View file @ e130cc6e
...@@ -283,7 +283,7 @@ For two micro-batch overlapping, you can refer to the following figure. With our ...@@ -283,7 +283,7 @@ For two micro-batch overlapping, you can refer to the following figure. With our
- [x] Refactor low-latency mode AR code - [x] Refactor low-latency mode AR code
- [ ] A100 support (intranode only) - [ ] A100 support (intranode only)
- [x] Support BF16 for the low-latency dispatch kernel - [x] Support BF16 for the low-latency dispatch kernel
- [ ] Support NVLink protocol for intranode low-latency kernels - [x] ~~Support NVLink protocol for intranode low-latency kernels~~ (conflict with hook-based overlapping)
- [ ] SM-free normal kernels - [ ] SM-free normal kernels
## Notices ## Notices
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment