-
Notifications
You must be signed in to change notification settings - Fork 12
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
Added a nb demonstrating efficient gpu utilizations #44
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
@suppathak What is pending in this PR? |
Thanks @Shreyanand for reminding me . I will clean it a bit and will conclude it. I will add other topics related to model compression in different notebooks. |
48f0e65
to
672f677
Compare
@@ -0,0 +1,476 @@ | |||
{ |
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.
@@ -0,0 +1,476 @@ | |||
{ |
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.
Do you mean with quantization?
Can you provide the percentage change in memory and inference time? it is more intuitive.
For inference time computation, can you run the cell 10 times and average the time? That makes the result more robust.
Reply via ReviewNB
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.
Requested some minor changes, majorly around adding source of the images and improving results.
Also, add this notebook in the resource section in the README.
Signed-off-by: Surya Prakash Pathak <[email protected]>
8e2222a
to
bdf592e
Compare
Related #36
Exploring:
What happens when we load the models in a lower precision format like INT-8? How is the accuracy, CPU, and memory performance affected? Explain theoretically and show results in a notebook. Touch upon challenges of frameworks like bitsandbytes in production.