mbs-octoml commented on a change in pull request #9749:
URL: https://github.com/apache/tvm/pull/9749#discussion_r770991464
##########
File path: src/relay/backend/te_compiler_cache.cc
##########
@@ -635,20 +640,16 @@ class MakeShapeFunc : public
backend::MemoizedExprTranslator<Array<te::Tensor>>
// Get output ndims
auto ret_type = call_node->checked_type();
Array<IndexExpr> out_ndims;
- if (const auto* ttype = ret_type.as<TensorTypeNode>()) {
+ for (const auto& ttype : FlattenTupleType(ret_type)) {
out_ndims.push_back(IntImm(DataType::Int(32), ttype->shape.size()));
Review comment:
Sorry, unrelated. Cleaning up flattening as I go.
--
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]
