diff --git a/deploy_45dim_rl_gym/bpu_deploy_s100/README.md b/deploy_45dim_rl_gym/bpu_deploy_s100/README.md
index 7aec824..6fbc3cd 100644
--- a/deploy_45dim_rl_gym/bpu_deploy_s100/README.md
+++ b/deploy_45dim_rl_gym/bpu_deploy_s100/README.md
@@ -130,6 +130,38 @@ Output: actions (1, 12)
 repeat=1000 avg_ms=0.733020
 ```
 
+纯 C++ BPU wrapper/bench，不经过 Python 推理路径：
+
+```bash
+cd /root/go1_pro_deploy/deploy_45dim_rl_gym/bpu_deploy_s100/cpp
+bash build_board.sh
+
+./s100_bpu_bench \
+  /root/go1_pro_deploy/deploy_45dim_rl_gym/bpu_quantization/mapper_output_26000_s100_gemm/policy_robotlab_26000_s100_int16_gemm.hbm \
+  /root/go1_pro_deploy/deploy_45dim_rl_gym/bpu_quantization/calibration_data_26000_robotlab_fast64/00000.bin \
+  1000 \
+  -1
+```
+
+参数含义：
+
+- 第 1 个参数：S100 `.hbm` 模型。
+- 第 2 个参数：float32 输入样本，当前 RobotLab 10 帧模型应为 450 个 float。
+- 第 3 个参数：重复推理次数。
+- 第 4 个参数：BPU core，`-1` 表示自动选择，`0..3` 表示固定单核。
+
+这个 C++ wrapper 只做离线推理：模型加载和 tensor 内存分配只初始化一次，循环里只做输入拷贝、cache flush、`hbDNNInferV2`、`hbUCPSubmitTask`、等待和输出拷贝。它不会连接机器人，也不会发送电机指令。
+
+当前板端纯 C++ 结果：
+
+```text
+backend=cpp_dnn_api_s100
+input_floats=450 output_floats=12 bpu_core=0
+action [0.544585 -1.108296 0.916061 -0.837005 0.074006 -0.434765 -0.858212 -2.766010 1.127831 0.422954 1.424179 -0.016353]
+action_max_abs 2.766010
+repeat=5000 cpp_avg_ms=0.426015
+```
+
 ## 离线推理检查
 
 这一步会连接 MCU 读取状态，但不会发送电机指令：
diff --git a/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/build_board.sh b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/build_board.sh
new file mode 100755
index 0000000..8eaf8b6
--- /dev/null
+++ b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/build_board.sh
@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+cd "$(dirname "$0")"
+
+CXX="${CXX:-g++}"
+CXXFLAGS=(
+  -O3
+  -DNDEBUG
+  -std=c++17
+  -Wall
+  -Wextra
+  -fPIC
+  -I/usr/include
+)
+LDFLAGS=(
+  -L/usr/hobot/lib
+  -ldnn
+  -lhbucp
+  -Wl,-rpath,/usr/hobot/lib
+)
+
+"${CXX}" "${CXXFLAGS[@]}" -shared s100_bpu_policy.cpp \
+  "${LDFLAGS[@]}" \
+  -o libs100_bpu_policy.so
+
+"${CXX}" "${CXXFLAGS[@]}" s100_bpu_bench.cpp \
+  -L. -ls100_bpu_policy -Wl,-rpath,'$ORIGIN' \
+  "${LDFLAGS[@]}" \
+  -o s100_bpu_bench
+
+echo "[OK] built $(pwd)/libs100_bpu_policy.so"
+echo "[OK] built $(pwd)/s100_bpu_bench"
diff --git a/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_bench.cpp b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_bench.cpp
new file mode 100644
index 0000000..e9c7eef
--- /dev/null
+++ b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_bench.cpp
@@ -0,0 +1,129 @@
+#include <algorithm>
+#include <chrono>
+#include <cmath>
+#include <cstdlib>
+#include <fstream>
+#include <iomanip>
+#include <iostream>
+#include <string>
+#include <vector>
+
+extern "C" {
+void *rlgym_s100_bpu_create(const char *model_path, int bpu_core, int priority,
+                            char *err, int err_len);
+int rlgym_s100_bpu_infer(void *handle, const float *input, float *output, char *err,
+                         int err_len);
+int rlgym_s100_bpu_input_floats(void *handle);
+int rlgym_s100_bpu_output_floats(void *handle);
+void rlgym_s100_bpu_destroy(void *handle);
+const char *rlgym_s100_bpu_version();
+}
+
+namespace {
+
+bool read_f32_file(const std::string &path, std::vector<float> *data) {
+  std::ifstream ifs(path, std::ios::binary);
+  if (!ifs) {
+    return false;
+  }
+  ifs.seekg(0, std::ios::end);
+  const auto size = ifs.tellg();
+  ifs.seekg(0, std::ios::beg);
+  if (size <= 0 || size % static_cast<std::streamoff>(sizeof(float)) != 0) {
+    return false;
+  }
+  data->resize(static_cast<size_t>(size) / sizeof(float));
+  ifs.read(reinterpret_cast<char *>(data->data()), size);
+  return ifs.good();
+}
+
+void print_usage(const char *argv0) {
+  std::cerr << "Usage: " << argv0 << " [model.hbm] [input.bin] [repeat] [bpu_core]\n"
+            << "  bpu_core: -1 means any core; 0..3 pins one BPU core\n";
+}
+
+}  // namespace
+
+int main(int argc, char **argv) {
+  const char *model =
+      "/root/go1_pro_deploy/deploy_45dim_rl_gym/bpu_quantization/"
+      "mapper_output_26000_s100_gemm/policy_robotlab_26000_s100_int16_gemm.hbm";
+  const char *input =
+      "/root/go1_pro_deploy/deploy_45dim_rl_gym/bpu_quantization/"
+      "calibration_data_26000_robotlab_fast64/00000.bin";
+  int repeat = 1000;
+  int bpu_core = -1;
+  if (argc > 1) model = argv[1];
+  if (argc > 2) input = argv[2];
+  if (argc > 3) repeat = std::atoi(argv[3]);
+  if (argc > 4) bpu_core = std::atoi(argv[4]);
+  if (argc > 5 || repeat <= 0) {
+    print_usage(argv[0]);
+    return 2;
+  }
+
+  char err[2048] = {};
+  void *handle = rlgym_s100_bpu_create(model, bpu_core, 0, err, sizeof(err));
+  if (handle == nullptr) {
+    std::cerr << err << "\n";
+    return 3;
+  }
+
+  const int input_floats = rlgym_s100_bpu_input_floats(handle);
+  const int output_floats = rlgym_s100_bpu_output_floats(handle);
+  if (input_floats <= 0 || output_floats <= 0) {
+    std::cerr << "invalid tensor sizes from S100 BPU runtime\n";
+    rlgym_s100_bpu_destroy(handle);
+    return 2;
+  }
+
+  std::vector<float> obs;
+  if (!read_f32_file(input, &obs) || static_cast<int>(obs.size()) != input_floats) {
+    std::cerr << "failed to read " << input_floats << " float32 input: " << input
+              << "\n";
+    rlgym_s100_bpu_destroy(handle);
+    return 2;
+  }
+
+  std::vector<float> out(static_cast<size_t>(output_floats), 0.0f);
+  if (rlgym_s100_bpu_infer(handle, obs.data(), out.data(), err, sizeof(err)) != 0) {
+    std::cerr << err << "\n";
+    rlgym_s100_bpu_destroy(handle);
+    return 4;
+  }
+
+  const auto t0 = std::chrono::steady_clock::now();
+  for (int i = 0; i < repeat; ++i) {
+    if (rlgym_s100_bpu_infer(handle, obs.data(), out.data(), err, sizeof(err)) != 0) {
+      std::cerr << err << "\n";
+      rlgym_s100_bpu_destroy(handle);
+      return 5;
+    }
+  }
+  const auto t1 = std::chrono::steady_clock::now();
+  const double elapsed_ms =
+      std::chrono::duration<double, std::milli>(t1 - t0).count();
+
+  const auto max_it = std::max_element(out.begin(), out.end(), [](float a, float b) {
+    return std::fabs(a) < std::fabs(b);
+  });
+
+  std::cout << "backend=" << rlgym_s100_bpu_version() << "\n";
+  std::cout << "input_floats=" << input_floats << " output_floats=" << output_floats
+            << " bpu_core=" << bpu_core << "\n";
+  std::cout << std::fixed << std::setprecision(6);
+  std::cout << "action [";
+  for (int i = 0; i < output_floats; ++i) {
+    if (i != 0) {
+      std::cout << ' ';
+    }
+    std::cout << out[static_cast<size_t>(i)];
+  }
+  std::cout << "]\n";
+  std::cout << "action_max_abs " << (max_it == out.end() ? 0.0f : std::fabs(*max_it))
+            << "\n";
+  std::cout << "repeat=" << repeat << " cpp_avg_ms=" << (elapsed_ms / repeat) << "\n";
+
+  rlgym_s100_bpu_destroy(handle);
+  return 0;
+}
diff --git a/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_policy.cpp b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_policy.cpp
new file mode 100644
index 0000000..82e55d6
--- /dev/null
+++ b/deploy_45dim_rl_gym/bpu_deploy_s100/cpp/s100_bpu_policy.cpp
@@ -0,0 +1,349 @@
+#include <algorithm>
+#include <cstdint>
+#include <cstdio>
+#include <cstring>
+#include <exception>
+#include <limits>
+#include <memory>
+#include <sstream>
+#include <stdexcept>
+#include <string>
+#include <vector>
+
+#include <hobot/dnn/hb_dnn.h>
+#include <hobot/dnn/hb_dnn_status.h>
+#include <hobot/hb_ucp.h>
+#include <hobot/hb_ucp_status.h>
+
+namespace {
+
+void set_error(char *err, int err_len, const std::string &msg) {
+  if (err == nullptr || err_len <= 0) {
+    return;
+  }
+  std::snprintf(err, static_cast<size_t>(err_len), "%s", msg.c_str());
+}
+
+std::string api_error(const std::string &where, int32_t code) {
+  std::ostringstream oss;
+  oss << where << " failed: " << code;
+  const char *desc = hbDNNGetErrorDesc(code);
+  if (desc == nullptr) {
+    desc = hbUCPGetErrorDesc(code);
+  }
+  if (desc != nullptr) {
+    oss << " (" << desc << ")";
+  }
+  return oss.str();
+}
+
+void check_api(int32_t code, const std::string &where) {
+  if (code != 0) {
+    throw std::runtime_error(api_error(where, code));
+  }
+}
+
+int64_t element_count(const hbDNNTensorShape &shape) {
+  int64_t count = 1;
+  for (int i = 0; i < shape.numDimensions; ++i) {
+    if (shape.dimensionSize[i] <= 0) {
+      throw std::runtime_error("dynamic or invalid tensor shape is not supported");
+    }
+    count *= shape.dimensionSize[i];
+  }
+  return count;
+}
+
+int element_size(int tensor_type) {
+  switch (tensor_type) {
+    case HB_DNN_TENSOR_TYPE_BOOL8:
+    case HB_DNN_TENSOR_TYPE_S8:
+    case HB_DNN_TENSOR_TYPE_U8:
+      return 1;
+    case HB_DNN_TENSOR_TYPE_F16:
+    case HB_DNN_TENSOR_TYPE_S16:
+    case HB_DNN_TENSOR_TYPE_U16:
+      return 2;
+    case HB_DNN_TENSOR_TYPE_F32:
+    case HB_DNN_TENSOR_TYPE_S32:
+    case HB_DNN_TENSOR_TYPE_U32:
+      return 4;
+    case HB_DNN_TENSOR_TYPE_F64:
+    case HB_DNN_TENSOR_TYPE_S64:
+    case HB_DNN_TENSOR_TYPE_U64:
+      return 8;
+    default:
+      throw std::runtime_error("unsupported tensor type");
+  }
+}
+
+int64_t compact_tail_bytes(const int32_t *dims, int dim_count, int elem_bytes) {
+  int64_t bytes = elem_bytes;
+  for (int i = 0; i < dim_count; ++i) {
+    bytes *= dims[i];
+  }
+  return bytes;
+}
+
+void copy_compact_to_strided(char *dst, const char *src, const hbDNNTensorProperties &props,
+                             int dim, int elem_bytes) {
+  const auto &shape = props.validShape;
+  if (dim + 1 == shape.numDimensions) {
+    std::memcpy(dst, src, static_cast<size_t>(shape.dimensionSize[dim] * elem_bytes));
+    return;
+  }
+
+  const int64_t src_step =
+      compact_tail_bytes(shape.dimensionSize + dim + 1, shape.numDimensions - dim - 1,
+                         elem_bytes);
+  const int64_t dst_step = props.stride[dim];
+  for (int i = 0; i < shape.dimensionSize[dim]; ++i) {
+    copy_compact_to_strided(dst + dst_step * i, src + src_step * i, props, dim + 1,
+                            elem_bytes);
+  }
+}
+
+void copy_strided_to_compact(char *dst, const char *src, const hbDNNTensorProperties &props,
+                             int dim, int elem_bytes) {
+  const auto &shape = props.validShape;
+  if (dim + 1 == shape.numDimensions) {
+    std::memcpy(dst, src, static_cast<size_t>(shape.dimensionSize[dim] * elem_bytes));
+    return;
+  }
+
+  const int64_t dst_step =
+      compact_tail_bytes(shape.dimensionSize + dim + 1, shape.numDimensions - dim - 1,
+                         elem_bytes);
+  const int64_t src_step = props.stride[dim];
+  for (int i = 0; i < shape.dimensionSize[dim]; ++i) {
+    copy_strided_to_compact(dst + dst_step * i, src + src_step * i, props, dim + 1,
+                            elem_bytes);
+  }
+}
+
+uint64_t core_mask_from_arg(int bpu_core) {
+  if (bpu_core < 0) {
+    return HB_UCP_BPU_CORE_ANY;
+  }
+  if (bpu_core > 3) {
+    throw std::runtime_error("bpu_core must be -1 or 0..3");
+  }
+  return 1ULL << static_cast<uint64_t>(bpu_core);
+}
+
+class S100BpuPolicy {
+ public:
+  S100BpuPolicy(const char *model_path, int bpu_core, int priority)
+      : bpu_core_mask_(core_mask_from_arg(bpu_core)), priority_(priority) {
+    if (model_path == nullptr || model_path[0] == '\0') {
+      throw std::runtime_error("empty model path");
+    }
+
+    const char *model_files[] = {model_path};
+    check_api(hbDNNInitializeFromFiles(&packed_handle_, model_files, 1),
+              "hbDNNInitializeFromFiles");
+
+    const char **model_names = nullptr;
+    int32_t model_count = 0;
+    check_api(hbDNNGetModelNameList(&model_names, &model_count, packed_handle_),
+              "hbDNNGetModelNameList");
+    if (model_count <= 0 || model_names == nullptr || model_names[0] == nullptr) {
+      throw std::runtime_error("model has no names");
+    }
+    model_name_ = model_names[0];
+    check_api(hbDNNGetModelHandle(&dnn_handle_, packed_handle_, model_names[0]),
+              "hbDNNGetModelHandle");
+
+    int32_t input_count = 0;
+    int32_t output_count = 0;
+    check_api(hbDNNGetInputCount(&input_count, dnn_handle_), "hbDNNGetInputCount");
+    check_api(hbDNNGetOutputCount(&output_count, dnn_handle_), "hbDNNGetOutputCount");
+    if (input_count != 1 || output_count != 1) {
+      std::ostringstream oss;
+      oss << "expected 1 input and 1 output, got " << input_count << " inputs and "
+          << output_count << " outputs";
+      throw std::runtime_error(oss.str());
+    }
+
+    input_tensors_.resize(1);
+    output_tensors_.resize(1);
+    check_api(hbDNNGetInputTensorProperties(&input_tensors_[0].properties, dnn_handle_, 0),
+              "hbDNNGetInputTensorProperties");
+    check_api(hbDNNGetOutputTensorProperties(&output_tensors_[0].properties, dnn_handle_, 0),
+              "hbDNNGetOutputTensorProperties");
+
+    validate_float_tensor(input_tensors_[0].properties, "input");
+    validate_float_tensor(output_tensors_[0].properties, "output");
+    input_floats_ = checked_float_count(input_tensors_[0].properties, "input");
+    output_floats_ = checked_float_count(output_tensors_[0].properties, "output");
+
+    alloc_tensor_mem(input_tensors_[0]);
+    alloc_tensor_mem(output_tensors_[0]);
+  }
+
+  ~S100BpuPolicy() {
+    release_tensor_mem(input_tensors_);
+    release_tensor_mem(output_tensors_);
+    if (packed_handle_ != nullptr) {
+      hbDNNRelease(packed_handle_);
+      packed_handle_ = nullptr;
+    }
+  }
+
+  void infer(const float *input, float *output) {
+    if (input == nullptr || output == nullptr) {
+      throw std::runtime_error("null input/output pointer");
+    }
+
+    auto &input_tensor = input_tensors_[0];
+    const auto &input_props = input_tensor.properties;
+    std::memset(input_tensor.sysMem.virAddr, 0,
+                static_cast<size_t>(input_props.alignedByteSize));
+    copy_compact_to_strided(reinterpret_cast<char *>(input_tensor.sysMem.virAddr),
+                            reinterpret_cast<const char *>(input), input_props, 0,
+                            sizeof(float));
+    check_api(hbUCPMemFlush(&input_tensor.sysMem, HB_SYS_MEM_CACHE_CLEAN),
+              "hbUCPMemFlush(input)");
+
+    hbUCPTaskHandle_t task_handle = nullptr;
+    check_api(hbDNNInferV2(&task_handle, output_tensors_.data(), input_tensors_.data(),
+                           dnn_handle_),
+              "hbDNNInferV2");
+
+    hbUCPSchedParam sched_param{};
+    HB_UCP_INITIALIZE_SCHED_PARAM(&sched_param);
+    sched_param.priority = priority_;
+    sched_param.backend = bpu_core_mask_;
+    try {
+      check_api(hbUCPSubmitTask(task_handle, &sched_param), "hbUCPSubmitTask");
+      check_api(hbUCPWaitTaskDone(task_handle, 0), "hbUCPWaitTaskDone");
+
+      auto &output_tensor = output_tensors_[0];
+      check_api(hbUCPMemFlush(&output_tensor.sysMem, HB_SYS_MEM_CACHE_INVALIDATE),
+                "hbUCPMemFlush(output)");
+      copy_strided_to_compact(reinterpret_cast<char *>(output),
+                              reinterpret_cast<const char *>(output_tensor.sysMem.virAddr),
+                              output_tensor.properties, 0, sizeof(float));
+    } catch (...) {
+      hbUCPReleaseTask(task_handle);
+      throw;
+    }
+
+    check_api(hbUCPReleaseTask(task_handle), "hbUCPReleaseTask");
+  }
+
+  int input_floats() const { return input_floats_; }
+  int output_floats() const { return output_floats_; }
+  const std::string &model_name() const { return model_name_; }
+
+ private:
+  static void validate_float_tensor(const hbDNNTensorProperties &props, const char *name) {
+    if (props.tensorType != HB_DNN_TENSOR_TYPE_F32) {
+      std::ostringstream oss;
+      oss << name << " tensor type " << props.tensorType << " != "
+          << HB_DNN_TENSOR_TYPE_F32;
+      throw std::runtime_error(oss.str());
+    }
+    if (props.alignedByteSize <= 0) {
+      throw std::runtime_error(std::string(name) + " alignedByteSize <= 0");
+    }
+    if (props.validShape.numDimensions <= 0) {
+      throw std::runtime_error(std::string(name) + " has invalid dimensions");
+    }
+  }
+
+  static int checked_float_count(const hbDNNTensorProperties &props, const char *name) {
+    const int64_t floats = element_count(props.validShape);
+    const int64_t bytes = floats * element_size(props.tensorType);
+    if (bytes > props.alignedByteSize) {
+      std::ostringstream oss;
+      oss << name << " compact bytes " << bytes << " > alignedByteSize "
+          << props.alignedByteSize;
+      throw std::runtime_error(oss.str());
+    }
+    if (floats > static_cast<int64_t>(std::numeric_limits<int>::max())) {
+      throw std::runtime_error(std::string(name) + " tensor is too large");
+    }
+    return static_cast<int>(floats);
+  }
+
+  static void alloc_tensor_mem(hbDNNTensor &tensor) {
+    std::memset(&tensor.sysMem, 0, sizeof(tensor.sysMem));
+    check_api(hbUCPMallocCached(&tensor.sysMem,
+                                static_cast<uint64_t>(tensor.properties.alignedByteSize), 0),
+              "hbUCPMallocCached");
+  }
+
+  static void release_tensor_mem(std::vector<hbDNNTensor> &tensors) {
+    for (auto &tensor : tensors) {
+      if (tensor.sysMem.virAddr != nullptr) {
+        hbUCPFree(&tensor.sysMem);
+        std::memset(&tensor.sysMem, 0, sizeof(tensor.sysMem));
+      }
+    }
+  }
+
+  hbDNNPackedHandle_t packed_handle_{nullptr};
+  hbDNNHandle_t dnn_handle_{nullptr};
+  std::string model_name_;
+  std::vector<hbDNNTensor> input_tensors_;
+  std::vector<hbDNNTensor> output_tensors_;
+  int input_floats_{0};
+  int output_floats_{0};
+  uint64_t bpu_core_mask_{HB_UCP_BPU_CORE_ANY};
+  int priority_{HB_UCP_PRIORITY_LOWEST};
+};
+
+}  // namespace
+
+extern "C" {
+
+void *rlgym_s100_bpu_create(const char *model_path, int bpu_core, int priority,
+                            char *err, int err_len) {
+  try {
+    set_error(err, err_len, "");
+    return new S100BpuPolicy(model_path, bpu_core, priority);
+  } catch (const std::exception &e) {
+    set_error(err, err_len, e.what());
+    return nullptr;
+  }
+}
+
+int rlgym_s100_bpu_infer(void *handle, const float *input, float *output, char *err,
+                         int err_len) {
+  try {
+    set_error(err, err_len, "");
+    if (handle == nullptr) {
+      throw std::runtime_error("null policy handle");
+    }
+    static_cast<S100BpuPolicy *>(handle)->infer(input, output);
+    return 0;
+  } catch (const std::exception &e) {
+    set_error(err, err_len, e.what());
+    return -1;
+  }
+}
+
+int rlgym_s100_bpu_input_floats(void *handle) {
+  if (handle == nullptr) {
+    return 0;
+  }
+  return static_cast<S100BpuPolicy *>(handle)->input_floats();
+}
+
+int rlgym_s100_bpu_output_floats(void *handle) {
+  if (handle == nullptr) {
+    return 0;
+  }
+  return static_cast<S100BpuPolicy *>(handle)->output_floats();
+}
+
+void rlgym_s100_bpu_destroy(void *handle) {
+  delete static_cast<S100BpuPolicy *>(handle);
+}
+
+const char *rlgym_s100_bpu_version() {
+  return "cpp_dnn_api_s100";
+}
+
+}
diff --git a/deploy_45dim_rl_gym/bpu_deploy_s100/deploy_go1_robotlab_bpu_s100_fastcpp.py b/deploy_45dim_rl_gym/bpu_deploy_s100/deploy_go1_robotlab_bpu_s100_fastcpp.py
index 5a26d50..bb13964 100644
--- a/deploy_45dim_rl_gym/bpu_deploy_s100/deploy_go1_robotlab_bpu_s100_fastcpp.py
+++ b/deploy_45dim_rl_gym/bpu_deploy_s100/deploy_go1_robotlab_bpu_s100_fastcpp.py
@@ -92,7 +92,7 @@ BPU_MODEL_REGISTRY = {
 }
 DEFAULT_BPU_ROUND = "26000"
 DEFAULT_BPU_MODEL = BPU_MODEL_REGISTRY[DEFAULT_BPU_ROUND]
-LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate_s100"
+LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate_cpp_udp_s100"
 SPORT_KILL_CMD = (
     'ssh pi@192.168.123.161 "sudo pkill -9 -f keep_sport_alive; '
     'sudo pkill -9 -f Legged_sport; sudo pkill -9 -f appTransit"'
diff --git a/deploy_45dim_rl_gym/bpu_deploy_x5/deploy_go1_robotlab_bpu_x5_fastcpp.py b/deploy_45dim_rl_gym/bpu_deploy_x5/deploy_go1_robotlab_bpu_x5_fastcpp.py
index 399cafb..45fa393 100644
--- a/deploy_45dim_rl_gym/bpu_deploy_x5/deploy_go1_robotlab_bpu_x5_fastcpp.py
+++ b/deploy_45dim_rl_gym/bpu_deploy_x5/deploy_go1_robotlab_bpu_x5_fastcpp.py
@@ -96,7 +96,7 @@ BPU_MODEL_REGISTRY = {
 }
 DEFAULT_BPU_ROUND = "26000"
 DEFAULT_BPU_MODEL = BPU_MODEL_REGISTRY[DEFAULT_BPU_ROUND]
-LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate"
+LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate_cpp_udp"
 SPORT_KILL_CMD = (
     'ssh pi@192.168.123.161 "sudo pkill -9 -f keep_sport_alive; '
     'sudo pkill -9 -f Legged_sport; sudo pkill -9 -f appTransit"'
diff --git a/deploy_45dim_rl_gym/deploy_go1_rlgym_bpu_x5_fastcpp.py b/deploy_45dim_rl_gym/deploy_go1_rlgym_bpu_x5_fastcpp.py
index 8dc0557..100ee2e 100644
--- a/deploy_45dim_rl_gym/deploy_go1_rlgym_bpu_x5_fastcpp.py
+++ b/deploy_45dim_rl_gym/deploy_go1_rlgym_bpu_x5_fastcpp.py
@@ -94,7 +94,7 @@ BPU_MODEL_REGISTRY = {
 }
 DEFAULT_BPU_ROUND = "35k"
 DEFAULT_BPU_MODEL = BPU_MODEL_REGISTRY[DEFAULT_BPU_ROUND]
-LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate"
+LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate_cpp_udp"
 SPORT_KILL_CMD = (
     'ssh pi@192.168.123.161 "sudo pkill -9 -f keep_sport_alive; '
     'sudo pkill -9 -f Legged_sport; sudo pkill -9 -f appTransit"'
diff --git a/deploy_45dim_rl_gym/deploy_go1_rlgym_pro_sdk_lab_fastcpp.py b/deploy_45dim_rl_gym/deploy_go1_rlgym_pro_sdk_lab_fastcpp.py
index 01974e3..417af46 100644
--- a/deploy_45dim_rl_gym/deploy_go1_rlgym_pro_sdk_lab_fastcpp.py
+++ b/deploy_45dim_rl_gym/deploy_go1_rlgym_pro_sdk_lab_fastcpp.py
@@ -85,7 +85,7 @@ except ImportError as exc:
     ) from exc
 
 DEFAULT_ONNX = HERE / "policy_robotlab_6500.onnx"
-LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate"
+LOWCMD_BACKEND = "cpp_lowcmd_cpp_lowstate_cpp_udp"
 SPORT_KILL_CMD = (
     'ssh pi@192.168.123.161 "sudo pkill -9 -f keep_sport_alive; '
     'sudo pkill -9 -f Legged_sport; sudo pkill -9 -f appTransit"'