piiswrong commented on a change in pull request #8719: Tune without Launch specialization macros URL: https://github.com/apache/incubator-mxnet/pull/8719#discussion_r152677681
########## File path: src/operator/tensor/init_op.h ########## @@ -263,16 +263,15 @@ void InitFillWithScalarCompute(const nnvm::NodeAttrs &attrs, CHECK_EQ(inputs.size(), 0); CHECK_EQ(outputs.size(), 1U); const auto& param = nnvm::get<InitOpWithScalarParam>(attrs.parsed); - Fill<true>(ctx.get_stream<xpu>(), outputs[0], req[0], param.value); + Fill<false>(ctx.get_stream<xpu>(), outputs[0], req[0], param.value); Review comment: ? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services