By pattern annotation: qnn.op.conv2d+nn.bias_add+qnn.op.requantize, it corresponds to a complete INT8 CONV with bias layer in Caffe. The code is too specific to the target hardware and I don't think it's more valuable than a generalized float32 conversion one. However, for fixed point accelerator, it should be always a requantize op followed at the end.
--- [Visit Topic](https://discuss.tvm.apache.org/t/parsing-relay-subgraph-with-composite-function-under-byoc/9407/6) 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/a1874558036d9322e3615296fd948dae134f8bed645da926d5764c0a151a8629).
