-
Notifications
You must be signed in to change notification settings - Fork 3.7k
Add FP32 dtype support for RoPE - Part1 #13181
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
|
Thanks for your review and triggering ci @FlamingoPg |
|
Hi @jinyouzhi , can you split this PR into two. The first part is the change on sgl-kernel side (which can be merged now I think), and the second part is the change on srt side. We need to bump sgl-kernel to make the srt change work |
Sure, great advice! I have followed it. |
Motivation
Fix #13124
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist