saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-10 17:37:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Enable ConvReplaceWithQLinear when using ACL (#22823)

Browse source 
### Description
Enable the ConvReplaceWithQLinear graph optimization when using the ACL
execution provider.



### Motivation and Context
Fixes an issue where quantized Conv nodes followed by ReLU don't get
converted to QLinearConv, so ACL sees the weights as mutable and
therefore cannot run the Conv node.

Signed-off-by: Michael Tyler <michael.tyler@arm.com>
This commit is contained in:
Michael Tyler 2024-11-14 05:44:50 +00:00 committed by GitHub
parent 82681205e4
commit dd99e34d66
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
onnxruntime/core/optimizer/qdq_transformer/selectors_actions/qdq_selector_action_transformer.cc
View file

@ -236,7 +236,7 @@ void ConvQDQRules(SelectorActionRegistry& qdq_selector_action_registry, bool is_
#if !defined(ORT_MINIMAL_BUILD)
// TODO: Enable 16-bit types in selector when QLinearConv supports 16-bit.
std::vector<const char*> providers = {kCpuExecutionProvider, kDmlExecutionProvider};
std::vector<const char*> providers = {kCpuExecutionProvider, kDmlExecutionProvider, kAclExecutionProvider};
std::unique_ptr<NodeSelector> selector = std::make_unique<QDQ::ConvSelector>(is_int8_allowed,
false,
false,