-
Notifications
You must be signed in to change notification settings - Fork 197
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
Feat: functionalize QuantTensor #878
Conversation
f32ecaf
to
0176483
Compare
c6f5216
to
368d0a3
Compare
d84ad1f
to
dbdb7e3
Compare
bit_width=output_bit_width, | ||
signed=output_signed, | ||
training=output_training) | ||
else: |
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.
@nickfraser I would like your opinion here
40ea5b4
to
1365296
Compare
Remove all max_acc_bit_width implementations from brevitas/nn |
Once your above changes have been done, this LGTM |
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.
Approved, conditional on the changes we discussed.
Depends on
#839,#880,#847,#883Outstanding layers:
HadamardClassifier-> Left for another PRQuantRNN and QuantLSTM(this might be challenging to abstract considering that we deal with proxys directly) -> Delayed indefinitely