-
Notifications
You must be signed in to change notification settings - Fork 169
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
Update README.md #140
Update README.md #140
Conversation
Update to include 1. the interoperability details 2. our goals 3. some general cleanup
README.md
Outdated
@@ -1,20 +1,30 @@ | |||
# torchao: PyTorch Architecture Optimization |
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.
first question i always get is what does ao mean so let's answer that somewheere in the first 3 lines
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.
I think this got deleted by mistake, I'll add it back
README.md
Outdated
## Key Features | ||
* Native PyTorch techniques, composable with torch.compile | ||
* APIs tested on following hardware - A100, T4(colab) | ||
* Supports the following eager quantization techniques. |
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.
so which techniques are compile specific and which are eager? If it's the same set then we can set say something like kernels that work with both eager and compile such as: int8 etc..
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.
I think they all work with both. @HDCharles or @jerryzh168 can you confirm?
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.
stamping since the update is urgent but hopefully the feedback is still useful
* Update README.md Update to include 1. the interoperability details 2. our goals 3. some general cleanup
Updates to include