Skip to content

S
Serving

PaddlePaddle / Serving
大约 1 年 前同步成功

通知 185
Star 833
Fork 253
S
Serving

体验新版 GitCode，发现更多精彩内容 >>

提交 a5cd92a7 编写于 作者: X xulongteng
浏览文件
操作

add memory optimize

上级 5f1a9f81
隐藏空白更改
内联 并排
Showing with 3 addition and 0 deletion
inferencer-fluid-gpu/include/fluid_gpu_engine.h
浏览文件 @ a5cd92a7
......@@ -133,6 +133,7 @@ class FluidGpuAnalysisCore : public FluidFamilyCore {
analysis_config.SetProgFile(data_path + "/__model__");
analysis_config.EnableUseGpu(100, FLAGS_gpuid);
analysis_config.SetCpuMathLibraryNumThreads(1);
analysis_config.EnableMemoryOptim(false, false);
analysis_config.SwitchSpecifyInputNames(true);
AutoLock lock(GlobalPaddleCreateMutex::instance());
_core =
......@@ -190,6 +191,7 @@ class FluidGpuAnalysisDirCore : public FluidFamilyCore {
analysis_config.EnableUseGpu(100, FLAGS_gpuid);
analysis_config.SwitchSpecifyInputNames(true);
analysis_config.SetCpuMathLibraryNumThreads(1);
analysis_config.EnableMemoryOptim(false, false);
AutoLock lock(GlobalPaddleCreateMutex::instance());
_core =
paddle::CreatePaddlePredictor<paddle::AnalysisConfig>(analysis_config);
......@@ -497,6 +499,7 @@ class FluidGpuAnalysisDirWithSigmoidCore : public FluidGpuWithSigmoidCore {
analysis_config.EnableUseGpu(100, FLAGS_gpuid);
analysis_config.SwitchSpecifyInputNames(true);
analysis_config.SetCpuMathLibraryNumThreads(1);
analysis_config.EnableMemoryOptim(false, false);
AutoLock lock(GlobalPaddleCreateMutex::instance());
_core->_fluid_core =
paddle::CreatePaddlePredictor<paddle::AnalysisConfig>(analysis_config);
......
Markdown is supported
0% 或 .
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 或