piotrwolinski-intel commented on code in PR #20987:
URL: https://github.com/apache/incubator-mxnet/pull/20987#discussion_r847247100
##########
src/operator/quantization/quantize.cc:
##########
@@ -47,6 +47,24 @@ bool QuantizeStorageType(const nnvm::NodeAttrs& attrs,
return true;
}
+#if MXNET_USE_ONEDNN == 1
+static void QuantizeComputeExCPU(const nnvm::NodeAttrs& attrs,
+ const OpContext& ctx,
+ const std::vector<NDArray>& inputs,
+ const std::vector<OpReqType>& req,
+ const std::vector<NDArray>& outputs) {
+ const QuantizeParam& param = nnvm::get<QuantizeParam>(attrs.parsed);
+
+ if (SupportDNNLQuantize(param.out_type)) {
Review Comment:
The problem is that `QuantizeParam` does not include fields needed for the
`GetQuantizeOutputType` (I mean `min_calib_range` and `max_calib_range`) so it
would also involve changing `QuantizeParam`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
