[Sampler] Add missing sync in gpu verifier (#2262)

Author: vinx13

cpp/serve/function_table.cc

@@ -135,7 +135,7 @@ void FunctionTable::Init(String reload_lib_path, Device device, picojson::object
         static_cast<int>(tvm::runtime::memory::AllocatorType::kPooled), static_cast<int>(kDLCPU), 0,
         static_cast<int>(tvm::runtime::memory::AllocatorType::kPooled));
     this->mod_get_func = [this](const std::string& name) -> PackedFunc {
-      return this->local_vm->GetFunction(name, false);
+      return this->local_vm->GetFunction(name, true);
     };
     this->get_global_func = [](const std::string& name) -> PackedFunc {
       const auto* f = tvm::runtime::Registry::Get(name);

cpp/serve/sampler/gpu_sampler.cc

@@ -244,6 +244,7 @@ class GPUSampler : public SamplerObj {
                                   token_tree_first_child_device, token_tree_next_sibling_device,
                                   uniform_samples_device, token_tree_parent_ptr_device);
 
+    DeviceAPI::Get(device_)->SyncStreamFromTo(device_, compute_stream_, copy_stream_);
     CopyArray(token_tree_parent_ptr_device, token_tree_parent_ptr_host, copy_stream_);
 
     std::vector<SampleResult> additional_sample_result;