[cherry-pick] inference fix trt problem (#35939)

* update xpu version

Author: jiweibo

cmake/external/lite.cmake

@@ -50,7 +50,7 @@ if (NOT LITE_SOURCE_DIR OR NOT LITE_BINARY_DIR)
   set(LITE_INSTALL_DIR ${THIRD_PARTY_PATH}/install/lite)
 
   if(NOT LITE_GIT_TAG)
-    set(LITE_GIT_TAG 1c4698c6efd9a5f57a4f8369bd5b6374166f5ba4)
+    set(LITE_GIT_TAG 4ab64daecc11fbf74fffdc6a4733f388472e7d5d)
   endif()
 
   if(NOT CUDA_ARCH_NAME)

cmake/external/xpu.cmake

@@ -35,7 +35,7 @@ ELSE ()
 ENDIF()
 
 SET(XPU_BASE_URL_WITHOUT_DATE "https://baidu-kunlun-product.cdn.bcebos.com/KL-SDK/klsdk-dev")
-SET(XPU_BASE_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210909")
+SET(XPU_BASE_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210921")
 SET(XPU_XRE_URL  "${XPU_BASE_URL}/${XPU_XRE_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)
 SET(XPU_XDNN_URL "${XPU_BASE_URL}/${XPU_XDNN_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)
 SET(XPU_XCCL_URL "${XPU_BASE_URL_WITHOUT_DATE}/20210623/${XPU_XCCL_DIR_NAME}.tar.gz" CACHE STRING "" FORCE)

paddle/fluid/inference/api/analysis_predictor.cc

@@ -686,9 +686,24 @@ void AnalysisPredictor::OptimizeInferenceProgram() {
 // Note, please do NOT use any member variables, because member variables may
 // have been destructed in multiple threads.
 #if PADDLE_WITH_TENSORRT
-        paddle::inference::Singleton<
-            inference::tensorrt::TRTEngineManager>::Global()
-            .DeleteAll();
+        auto &block = prog->Block(0);
+        for (auto &op_desc : block.AllOps()) {
+          if (op_desc->Type() == "tensorrt_engine") {
+            std::string engine_key =
+                BOOST_GET_CONST(std::string, op_desc->GetAttr("engine_key"));
+            int engine_predictor_id =
+                BOOST_GET_CONST(int, op_desc->GetAttr("predictor_id"));
+            std::string engine_name =
+                engine_key + std::to_string(engine_predictor_id);
+            if (paddle::inference::Singleton<
+                    inference::tensorrt::TRTEngineManager>::Global()
+                    .Has(engine_name)) {
+              paddle::inference::Singleton<
+                  inference::tensorrt::TRTEngineManager>::Global()
+                  .DeleteKey(engine_name);
+            }
+          }
+        }
 #endif
         delete prog;
       });

paddle/fluid/inference/tensorrt/engine.h

@@ -631,6 +631,14 @@ class TRTEngineManager {
     }
   }
 
+  void DeleteKey(const std::string& key) {
+    auto iter = engines_.find(key);
+    if (iter != engines_.end()) {
+      iter->second.reset(nullptr);
+      engines_.erase(iter);
+    }
+  }
+
  private:
   std::unordered_map<std::string, std::unique_ptr<TensorRTEngine>> engines_;
 };