slove develop bugs (#32560)

paddle/fluid/operators/collective/c_sync_comm_stream_op.cc

@@ -63,7 +63,6 @@ class CSyncCommStreamCudaKernel : public framework::OpKernel<T> {
   void Compute(const framework::ExecutionContext& ctx) const override {
     auto place = ctx.GetPlace();
 #if defined(PADDLE_WITH_NCCL) || defined(PADDLE_WITH_RCCL)
-
     int ring_id = ctx.Attr<int>("ring_id");
     auto stream =
         platform::NCCLCommContext::Instance().Get(ring_id, place)->stream();
@@ -75,7 +74,6 @@ class CSyncCommStreamCudaKernel : public framework::OpKernel<T> {
 #endif
 
 #elif defined(PADDLE_WITH_ASCEND_CL)
-    auto place = ctx.GetPlace();
     PADDLE_ENFORCE_EQ(is_npu_place(place), true,
                       platform::errors::PreconditionNotMet(
                           "Sync stream op can run on npu place only for now."));

paddle/fluid/pybind/ascend_wrapper_py.cc

@@ -108,12 +108,14 @@ enum AttrType {
   AT_NAMEATTR
 };
 
+#ifdef PADDLE_WITH_ASCEND
 void BindAscendDevice(py::module *m) {
   py::class_<platform::ascend::NPUDevice>(*m, "NPUDevice")
       .def_static(
           "get_device_count",
           static_cast<int (*)()>(&platform::ascend::NPUDevice::GetDeviceCount));
 }
+#endif
 
 void BindAscendGraph(py::module *m) {
   m->def("ge_initialize", &ge_initialize, "GEInitialize");

python/paddle/distributed/fleet/launch.py

@@ -325,8 +325,8 @@ def which_distributed_mode(args):
 
     if fluid.core.is_compiled_with_cuda():
         accelerators = fluid.core.get_cuda_device_count()
-    elif fluid.core.is_compiled_with_ascend():
-        accelerators = fluid.core.NPUDevice.get_device_count()
+    elif fluid.core.is_compiled_with_npu():
+        accelerators = fluid.core.get_npu_device_count()
     elif fluid.core.is_compiled_with_xpu():
         accelerators = fluid.core.get_xpu_device_count()
     else:

python/paddle/distributed/fleet/launch_utils.py

@@ -653,8 +653,8 @@ def get_xpus(xpus):
 
 
 def get_device_mode():
-    if fluid.core.is_compiled_with_ascend() and \
-            fluid.core.NPUDevice.get_device_count() > 0:
+    if fluid.core.is_compiled_with_npu() and \
+            fluid.core.get_npu_device_count() > 0:
         print("launch train in ascend npu mode!")
         return DeviceMode.ASCEND_NPU