Ernie enable_mkldnn_int8 crash on matmul

[lidanqing-intel]

bug描述 Describe the Bug

git clone [https://github.com/PaddlePaddle/PaddleNLP.git](https://mailshield.baidu.com/check?q=k8BkYPPp7mp%2b7Nbe1f9l531szTtS4PX3rtTD4gps4%2b2a4RBAzaTvqDyUbzG4FYaoG42LhQ%3d%3d)
cd PaddleNLP
pip install -r requirements.txt
python setup.py install
cd examples/language_model/ernie-3.0
 python infer.py --task_name tnews --model_path /home/guest/PaddleNLP/model_zoo/ernie-3.0/ernie-3.0/int8 --perf --device cpu --num_threads 8

其他补充信息 Additional Supplementary Information

RuntimeError:

--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
1   std::unique_ptr<paddle::PaddlePredictor, std::default_delete<paddle::PaddlePredictor> > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
2   paddle::AnalysisPredictor::Init(std::shared_ptr<paddle::framework::Scope> const&, std::shared_ptr<paddle::framework::ProgramDesc> const&)
3   paddle::AnalysisPredictor::PrepareProgram(std::shared_ptr<paddle::framework::ProgramDesc> const&)
4   paddle::AnalysisPredictor::OptimizeInferenceProgram()
5   paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
6   paddle::inference::analysis::IrAnalysisPass::RunImpl(paddle::inference::analysis::Argument*)
7   paddle::inference::analysis::IRPassManager::Apply(std::unique_ptr<paddle::framework::ir::Graph, std::default_delete<paddle::framework::ir::Graph> >)
8   paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
9   paddle::framework::ir::QuantDequantMkldnnPass::ApplyImpl(paddle::framework::ir::Graph*) const
10  paddle::framework::ir::QuantDequantMkldnnPass::DequantizeWeights(paddle::framework::ir::Graph*, paddle::framework::Scope*, std::unordered_map<std::string, std::vector<float, std::allocator<float> >, std::hash<std::string >, std::equal_to<std::string >, std::allocator<std::pair<std::string const, std::vector<float, std::allocator<float> > > > > const&) const
11  paddle::framework::ir::QuantDequantMkldnnPass::IsInt8Weight(paddle::framework::ir::Node*, paddle::framework::Scope*, std::string const&) const
12  phi::enforce::EnforceNotMet::EnforceNotMet(phi::ErrorSummary const&, char const*, int)
13  phi::enforce::GetCurrentTraceBackString[abi:cxx11](bool)

----------------------
Error Message Summary:
----------------------
NotFoundError: The input persistable [transpose_1.tmp_0] var of [matmul] op is not found.
  [Hint: var should not be null.] (at /home/Paddle/paddle/fluid/framework/ir/mkldnn/quant_dequant_mkldnn_pass.cc:356)

[lidanqing-intel]

#43297 fix this issue

[lidanqing-intel]

#43297 is merged