[slimtensor] Add CUDA slimtensor creation with basic functionality

backends/aoti/slim/core/SlimTensor.h

@@ -227,6 +227,13 @@ class SlimTensor {
     return device().is_cpu();
   }
 
+  /**
+   * Check if the tensor is on CUDA.
+   */
+  bool is_cuda() const {
+    return device().is_cuda();
+  }
+
   /**
    * Check if the tensor is defined (has valid storage).
    */

backends/aoti/slim/core/targets.bzl

@@ -22,7 +22,6 @@ def define_common_targets():
         ],
     )
 
-    # Header-only library for SlimTensor (CPU-only for now)
     runtime.cxx_library(
         name = "slimtensor",
         headers = [
@@ -37,6 +36,8 @@ def define_common_targets():
             "//executorch/backends/aoti/slim/c10/core:sizes_and_strides",
             "//executorch/backends/aoti/slim/util:array_ref_util",
             "//executorch/backends/aoti/slim/util:size_util",
+            "//executorch/backends/aoti/slim/c10/cuda:exception",
+            "//executorch/backends/aoti/slim/cuda:guard",
             "//executorch/runtime/platform:platform",
         ],
     )

backends/aoti/slim/core/test/targets.bzl

@@ -32,16 +32,17 @@ def define_common_targets():
             **backend_kwargs
         )
 
-    runtime.cxx_test(
-        name = "test_slimtensor_basic",
-        srcs = [
-            "test_slimtensor_basic.cpp",
-        ],
-        deps = [
-            "//executorch/backends/aoti/slim/core:slimtensor",
-            "//executorch/backends/aoti/slim/core:storage",
-        ],
-    )
+        runtime.cxx_test(
+            name = "test_slimtensor_basic"  + backend_suffix,
+            srcs = [
+                "test_slimtensor_basic.cpp",
+            ],
+            deps = [
+                "//executorch/backends/aoti/slim/core:slimtensor",
+                "//executorch/backends/aoti/slim/core:storage",
+            ],
+            **backend_kwargs
+        )
 
     runtime.cxx_test(
         name = "test_slimtensor_copy",

backends/aoti/slim/core/test/test_slimtensor_basic.cpp

@@ -21,6 +21,9 @@ namespace executorch::backends::aoti::slim {
 inline std::vector<c10::Device> get_test_devices() {
   std::vector<c10::Device> devices;
   devices.push_back(CPU_DEVICE);
+#ifdef CUDA_AVAILABLE
+  devices.push_back(DEFAULT_CUDA_DEVICE);
+#endif
   return devices;
 }
 
@@ -52,7 +55,9 @@ INSTANTIATE_TEST_SUITE_P(
     DeviceTests,
     SlimTensorBasicDeviceTest,
     ::testing::ValuesIn(get_test_devices()),
-    [](const ::testing::TestParamInfo<c10::Device>& info) { return "CPU"; });
+    [](const ::testing::TestParamInfo<c10::Device>& info) {
+      return info.param.is_cuda() ? "CUDA" : "CPU";
+    });
 
 // =============================================================================
 // Constructor Tests (Device-Parameterized)

backends/aoti/slim/factory/Empty.h

@@ -23,7 +23,7 @@ namespace executorch::backends::aoti::slim {
 /// @param sizes The sizes of each dimension.
 /// @param strides The strides of each dimension.
 /// @param dtype The scalar type of tensor elements.
-/// @param device The target device (must be CPU).
+/// @param device The target device.
 /// @return A new SlimTensor with allocated but uninitialized storage.
 inline SlimTensor empty_strided(
     IntArrayRef sizes,
@@ -41,7 +41,7 @@ inline SlimTensor empty_strided(
 ///
 /// @param sizes The sizes of each dimension.
 /// @param dtype The scalar type of tensor elements.
-/// @param device The target device (must be CPU).
+/// @param device The target device.
 /// @return A new SlimTensor with contiguous strides and uninitialized storage.
 inline SlimTensor empty(
     IntArrayRef sizes,
@@ -59,7 +59,7 @@ inline SlimTensor empty(
 ///
 /// @param sizes The sizes of each dimension as an initializer list.
 /// @param dtype The scalar type of tensor elements.
-/// @param device The target device (must be CPU).
+/// @param device The target device.
 /// @return A new SlimTensor with contiguous strides and uninitialized storage.
 inline SlimTensor empty(
     std::initializer_list<int64_t> sizes,

backends/aoti/slim/factory/test/targets.bzl

@@ -1,14 +1,33 @@
+load("@fbcode_macros//build_defs/lib:re_test_utils.bzl", "re_test_utils")
 load("@fbsource//xplat/executorch/build:runtime_wrapper.bzl", "runtime")
 
+def get_backend_mode():
+    """Get the supported backend mode of slimtensor."""
+    return ["cuda", "cpu"]
+
 def define_common_targets():
     """Define test targets for SlimTensor factory module."""
 
-    runtime.cxx_test(
-        name = "test_empty",
-        srcs = [
-            "test_empty.cpp",
-        ],
-        deps = [
-            "//executorch/backends/aoti/slim/factory:empty",
-        ],
-    )
+    # GPU empty test with CUDA support
+    for backend_mode in get_backend_mode():
+        backend_suffix = "_" + backend_mode if backend_mode == "cuda" else ""
+
+        backend_kwargs = {
+            "external_deps": [("cuda", None, "cuda-lazy")],
+            "preprocessor_flags": ["-DCUDA_AVAILABLE=1"],
+            "keep_gpu_sections": True,
+            "remote_execution": re_test_utils.remote_execution(
+                platform = "gpu-remote-execution",
+            ),
+        } if backend_mode == "cuda" else {}
+
+        runtime.cxx_test(
+            name = "test_empty" + backend_suffix,
+            srcs = [
+                "test_empty.cpp",
+            ],
+            deps = [
+                "//executorch/backends/aoti/slim/factory:empty",
+            ],
+            **backend_kwargs
+        )