-
Notifications
You must be signed in to change notification settings - Fork 158
[WIP] a16w4 int4 support #1559
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
base: main
Are you sure you want to change the base?
[WIP] a16w4 int4 support #1559
Conversation
|
|
||
| a_type = "bf16" | ||
| b_type = "fp4" | ||
| b_type = "i4" |
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.
Why remove fp4 here?
| ) | ||
| a2 = a2.view(token_num, topk, inter_dim) | ||
|
|
||
| sorted_weights_value = sorted_weights if not doweight_stage1 else None |
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 the a16w4 support the "doweight_stage1 "?
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 don't know where the line coming from. Maybe it comes from my incorrect conflict reolsve. It seems that it has nothing to do with a16w4 feature. Remove it later.
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist