-
Notifications
You must be signed in to change notification settings - Fork 519
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
Add benchmarks to inference README #393
Conversation
Co-authored-by: Vitaliy Chiley <6439018+vchiley@users.noreply.github.com>
Co-authored-by: Vitaliy Chiley <6439018+vchiley@users.noreply.github.com>
Co-authored-by: Vitaliy Chiley <6439018+vchiley@users.noreply.github.com>
… into inference_readme
Co-authored-by: Vitaliy Chiley <6439018+vchiley@users.noreply.github.com>
Co-authored-by: Vitaliy Chiley <6439018+vchiley@users.noreply.github.com>
… into inference_readme
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The colors/linestyles of the MPT-30B latency-throughput curve need to be fixed a bit:
- 80GB = blue, 40GB = green
- 1 GPU = dash, 2GPU = dots, 4GPu = solid
this way it will match the 7B plot which looks excellent!
If possible I would also recommend standardizing the colors of the plots with latency @ token length. Sometihng like
so people can quickly look from one plot to the next and compare |
@abhi-mosaic fixing plots now! |
Include benchmark info