-
Notifications
You must be signed in to change notification settings - Fork 1.8k
Conversation
output that needs to be quantized | ||
config : dict | ||
the configuration for output quantization | ||
""" |
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.
new_output
undefine?
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.
Oh, I follow the quantize_weight
format. This means user needs to return a tensor, which is the quantized output.
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.
OK. At least add ...
here?
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.
Sure. ...
will make more sense.
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 add a comment
# Put your code to generate `new_input` here
return new_input
I think this will be more clear.
No description provided.