saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-26 03:00:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temporarily disable weight/Bias quantization

Browse source
This commit is contained in:
Chi Lo 2025-01-22 10:15:16 -08:00
parent bbb5862b9e
commit 981d95b81e
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/graph_transformer_utils.cc
View file

@ -249,7 +249,7 @@ InlinedVector<std::unique_ptr<GraphTransformer>> GenerateTransformers(
if (!disable_quant_qdq) {
transformers.emplace_back(std::make_unique<QDQPropagationTransformer>());
transformers.emplace_back(std::make_unique<WeightBiasQuantization>());
//transformers.emplace_back(std::make_unique<WeightBiasQuantization>());
// EnsureUniqueDQForNodeUnit is actually a required graph transformation. The unique DQ per QDQ node unit input
// condition that it ensures is important for the partitioning that happens after Level1 optimizers are run.