Quantized models and legalization pass

Sorry for late reply. Can you try this? tinfo is nothing but just te placeholder.

diff --git a/python/tvm/relay/qnn/op/legalizations.py b/python/tvm/relay/qnn/op/legalizations.py
index 50e5a02f8..8add434c1 100644
--- a/python/tvm/relay/qnn/op/legalizations.py
+++ b/python/tvm/relay/qnn/op/legalizations.py
@@ -295,6 +295,10 @@ def _qnn_dense_legalize_arm_cpu(attrs, inputs, types):
 @qnn_conv2d_legalize.register("cpu")
 def _qnn_conv2d_legalize_intel_cpu(attrs, inputs, types):
     # The VNNI transformations prefer uint8 x int8 datatypes.
+    data_type = types[0]
+    data_tinfo = tvm.te.placeholder(shape=data_type.shape, dtype=data_type.dtype)
+    print(data_tinfo)
+
     if is_fast_int8_on_intel():
         return helper_change_dtypes_to_uint8_int8(attrs, inputs, types, relay.qnn.op.conv2d)
     return helper_no_fast_int8_hw_legalization(attrs, inputs, types, relay.nn.conv2d)

If not, we can change Legalize to accept one more argument, but thats more invasive.