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.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/quantized-models-and-legalization-pass/8253/7)
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/15057ce82eacb50e35df26abbc9bdb2499fad0067042af67e1721568a70c67a9).
