未验证 提交 7d13d207 编写于 作者: T Tao Luo 提交者: GitHub

Merge pull request #15245 from luotao1/rnn1_multi_thread

reduce threads number to avoid analyzer_rnn1_tester hang in CI
......@@ -283,7 +283,7 @@ TEST(Analyzer_rnn1, multi_thread) {
std::vector<std::vector<PaddleTensor>> input_slots_all;
SetInput(&input_slots_all);
TestPrediction(reinterpret_cast<const PaddlePredictor::Config *>(&cfg),
input_slots_all, &outputs, 4 /* multi_thread */);
input_slots_all, &outputs, 2 /* multi_thread */);
}
// Validate that the AnalysisPredictor + ZeroCopyTensor really works by testing
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册