zhiics commented on a change in pull request #5153: Adding support for QNN
subtract op
URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398855417
##########
File path: src/relay/qnn/op/op_common.h
##########
@@ -30,14 +30,151 @@
#include <tvm/relay/qnn/attrs.h>
#include <vector>
#include "../../op/type_relations.h"
+#include "../../transforms/infer_layout_util.h"
+#include "../util.h"
namespace tvm {
namespace relay {
namespace qnn {
-static inline bool QnnBroadcastRel(const Array<Type>& types, int num_inputs,
const Attrs& attrs,
+/*
+ * Number of inputs for the Qnn binary operators.
+ * Refer the QNN_REGISTER_BINARY_OP macro to see
+ * what the operators are.
+ */
+static constexpr int numQnnBinaryOpInputs = 8;
Review comment:
usually we use `kNumQnnBinaryOpInputs` for consts
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
