CUDA sparsity support (#36413) (#36659)

PaddlePaddle · Oct 25, 2021 · 6ecfe80 · 6ecfe80
1 parent 8ebee86
commit 6ecfe80
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/paddle/fluid/inference/tensorrt/engine.cc b/paddle/fluid/inference/tensorrt/engine.cc
@@ -238,6 +238,7 @@ void TensorRTEngine::FreezeNetwork() {
   infer_engine_.reset(infer_builder_->buildEngineWithConfig(
       *network(), *infer_builder_config_));
 #else
+  infer_builder_config_->setFlag(nvinfer1::BuilderFlag::kSPARSE_WEIGHTS);
   infer_ptr<nvinfer1::IHostMemory> plan(infer_builder_->buildSerializedNetwork(
       *network(), *infer_builder_config_));
   infer_ptr<nvinfer1::IRuntime> runtime(createInferRuntime(&logger_));