Also, as part of the standardization of QNN, we could ensure that all QNN "compute" ops go from `int8 -> int8` . I believe that `qnn.conv2d` is the only QNN op that outputs an accumulation dtype, so we could change `qnn.conv2d` to take in bias in addition to the data and weight.
--- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-quantization-a-new-quantization-framework-in-tvm-initial-rfc-1-4/9775/24) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/1820bb9f1fb33b6b3299666fed911f862722188ff19ad44e856268522d3f8df2).
