Jan-Frederik Schulte
Jan-Frederik Schulte
Hi @JiaMingLin Thanks for testing out this feature. I have been looking at it and I am beginning to realize that I have overlooked some complications with parsing from brevitas...
We now support the quantization of input and output tensors of `QuantLinear`, `QuantConv1D`, and `QuantConv2D` and `QuantActivation` layers. Only quantization with scales equaling powers of 2 are supported at the...
Hey @jmitrevs I can't reproduce the oneAPI compilation error in the `test_brevitas_parsing` pytest locally for some reason. I'm suspecting it's genuine, but it's hard to tell because locally it compiles...
To summarize the current state of this: I think this PR contains what we can reasonably support currently and most things work somewhat well. Everything is limited to power-of-2 scales,but...
Removed QuantLSTM for now. QuantRNN is also not great, but at least usually gets results in the same ballpark. Otherwise I think this is ready for review.
pre-commit.ci autofix
pre-commit.ci autofix
I wanted to try to install oneAPI myself, so I played with this PR a bit. The issue seems to be that the precision for the parameter of the leaky...
Hey @nghielme any news on this one?
There were some weird pytest failures that I'm rerunning, but otherwise I think this can be merged now.