diff --git a/dipu/SupportedDiopiFunctions.txt b/dipu/SupportedDiopiFunctions.txt
index 547e75955..0f6a3b0ff 100644
--- a/dipu/SupportedDiopiFunctions.txt
+++ b/dipu/SupportedDiopiFunctions.txt
@@ -101,6 +101,7 @@ diopiForeachmulInpTensor
 diopiForeachmulScalar
 diopiForeachmulTensor
 diopiForeachnormScalar
+diopiFusedAdamW
 diopiGather
 diopiGe
 diopiGeInp
diff --git a/dipu/scripts/autogen_diopi_wrapper/diopi_functions.yaml b/dipu/scripts/autogen_diopi_wrapper/diopi_functions.yaml
index 2759f7fb6..8e3b03ff0 100755
--- a/dipu/scripts/autogen_diopi_wrapper/diopi_functions.yaml
+++ b/dipu/scripts/autogen_diopi_wrapper/diopi_functions.yaml
@@ -1325,6 +1325,42 @@
     ::diopiConstTensorHandle_t self_dtype_diopi = dipu::diopi_helper::toDiopiTensorHandle(self_dtype);
   interface: diopiProd(ctx, out, self_dtype_diopi, nullptr)
 
+- schema: "_fused_adamw_(Tensor(a!)[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, float lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None) -> ()"
+  custom_code_at_the_beginning: |
+    std::vector<diopiTensorHandle_t> diopiTensorHandles_self(self.size());
+    for(size_t i=0; i < self.size(); ++i){
+      diopiConstTensorHandle_t const_handle = dipu::diopi_helper::toDiopiTensorHandle(self.at(i));
+      diopiTensorHandle_t handle = const_cast<diopiTensorHandle_t>(const_handle);
+      diopiTensorHandles_self[i] = handle;
+    }
+    std::vector<diopiConstTensorHandle_t> diopiTensorHandles_grads(grads.size());
+    for(size_t i=0; i < grads.size(); ++i){
+      diopiTensorHandles_grads[i] = dipu::diopi_helper::toDiopiTensorHandle(grads.at(i));
+    }
+    std::vector<diopiTensorHandle_t> diopiTensorHandles_exp_avgs(exp_avgs.size());
+    for(size_t i=0; i < exp_avgs.size(); ++i){
+      diopiConstTensorHandle_t const_handle = dipu::diopi_helper::toDiopiTensorHandle(exp_avgs.at(i));
+      diopiTensorHandle_t handle = const_cast<diopiTensorHandle_t>(const_handle);
+      diopiTensorHandles_exp_avgs[i] = handle;
+    }
+    std::vector<diopiTensorHandle_t> diopiTensorHandles_exp_avg_sqs(exp_avg_sqs.size());
+    for(size_t i=0; i < exp_avg_sqs.size(); ++i){
+      diopiConstTensorHandle_t const_handle = dipu::diopi_helper::toDiopiTensorHandle(exp_avg_sqs.at(i));
+      diopiTensorHandle_t handle = const_cast<diopiTensorHandle_t>(const_handle);
+      diopiTensorHandles_exp_avg_sqs[i] = handle;
+    }
+    std::vector<diopiTensorHandle_t> diopiTensorHandles_max_exp_avg_sqs(max_exp_avg_sqs.size());
+    for(size_t i=0; i < max_exp_avg_sqs.size(); ++i){
+      diopiConstTensorHandle_t const_handle = dipu::diopi_helper::toDiopiTensorHandle(max_exp_avg_sqs.at(i));
+      diopiTensorHandle_t handle = const_cast<diopiTensorHandle_t>(const_handle);
+      diopiTensorHandles_max_exp_avg_sqs[i] = handle;
+    }
+    std::vector<diopiConstTensorHandle_t> diopiTensorHandles_state_steps(state_steps.size(), nullptr);
+    for(size_t i=0; i < state_steps.size(); ++i){
+      diopiTensorHandles_state_steps[i] = dipu::diopi_helper::toDiopiTensorHandle(state_steps.at(i));
+    }
+  interface: diopiFusedAdamW(ctx, diopiTensorHandles_self.data(), diopiTensorHandles_grads.data(), diopiTensorHandles_exp_avgs.data(), diopiTensorHandles_exp_avg_sqs.data(), diopiTensorHandles_max_exp_avg_sqs.data(), diopiTensorHandles_state_steps.data(), static_cast<int64_t>(self.size()), lr, beta1, beta2, eps, weight_decay, amsgrad, maximize)
+
 - schema: prod.int_out(Tensor self, int dim, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)
   custom_code_at_the_beginning: |
     const auto self_dtype = at::native::to(self, dtype);
diff --git a/dipu/third_party/DIOPI b/dipu/third_party/DIOPI
index 65930a539..02f03c6ab 160000
--- a/dipu/third_party/DIOPI
+++ b/dipu/third_party/DIOPI
@@ -1 +1 @@
-Subproject commit 65930a539938b692a84ba77027e91686b3d2516d
+Subproject commit 02f03c6abb20aa39d1d978436a53a2e4ec242d65