Bump the PyTorch pin to 2.14

.ci/docker/ci_commit_pins/pytorch.txt

@@ -1 +1 @@
-release/2.13
+release/2.14

.ci/docker/common/install_docs_reqs.sh

@@ -20,7 +20,9 @@ if [ -n "$BUILD_DOCS" ]; then
 
   apt-get update
   apt-get install -y --no-install-recommends yarn
-  yarn global add katex --prefix /usr/local
+  # katex 0.18.5 requires commander@15 / node >= 22.12; pin to the last
+  # release compatible with the node 16 installed above
+  yarn global add katex@0.18.4 --prefix /usr/local
 
   sudo apt-get -y install doxygen
 

.ci/docker/common/install_pytorch.sh

@@ -76,21 +76,31 @@ install_pytorch_and_domains() {
   # the image compiler cannot satisfy. The venv inherits the image's
   # site-packages, so PyTorch still builds against the same numpy.
   #
-  # Keep the list in sync with pytorch/pyproject.toml [build-system].requires.
+  # Keep in sync with pytorch/pyproject.toml [build-system].requires.
   local build_venv=/tmp/pytorch-build-venv
   rm -rf "${build_venv}"
   conda_run python -m venv --system-site-packages "${build_venv}"
+  # No pip cmake: scikit-build-core would prefer it over the image's, and it
+  # searches site-packages, where MKL and libomp are not.
   conda_run "${build_venv}/bin/pip" install build "scikit-build-core>=1.0" \
-    "setuptools>=77.0.0,<82" "cmake>=3.27,<4" ninja "packaging>=24.2" \
-    "typing-extensions>=4.10.0" pyyaml six
-  conda_run "${build_venv}/bin/python" -m build --wheel --no-isolation
+    ninja "packaging>=24.2" "typing-extensions>=4.10.0" pyyaml six numpy
+  # These images have no module scanner, and nothing here uses modules.
+  conda_run env CMAKE_CXX_SCAN_FOR_MODULES=OFF \
+    "${build_venv}/bin/python" -m build --wheel --no-isolation
   rm -rf "${build_venv}"
   pip_install "$(echo dist/*.whl)"
 
+  # A build with no BLAS succeeds silently. Run from / to import the wheel.
+  (cd / && conda_run python -c "
+import torch
+assert torch._C.has_lapack, 'built without LAPACK'
+torch.linalg.qr(torch.randn(4, 4))
+")
+
   # Grab the pinned audio and vision commits from PyTorch
   TORCHAUDIO_VERSION=release/2.11
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.28
+  TORCHVISION_VERSION=release/0.29
   export TORCHVISION_VERSION
 
   install_domains

.ci/scripts/test-rocm-aoti.sh

@@ -7,7 +7,7 @@
 
 set -euo pipefail
 
-ROCM_VERSION="${ROCM_VERSION:-7.1}"
+ROCM_VERSION="${ROCM_VERSION:-7.2}"
 ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
 PYTORCH_ROCM_INDEX="${PYTORCH_ROCM_INDEX:-https://download.pytorch.org/whl/test/rocm${ROCM_VERSION}}"
 TORCHAO_ROCM_WHEEL_BASE="${TORCHAO_ROCM_WHEEL_BASE:-https://download.pytorch.org/whl/nightly/rocm${ROCM_VERSION}}"

.ci/scripts/test-rocm-voxtral.sh

@@ -7,7 +7,7 @@
 
 set -euo pipefail
 
-ROCM_VERSION="${ROCM_VERSION:-7.1}"
+ROCM_VERSION="${ROCM_VERSION:-7.2}"
 ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
 EXPECTED_ROCM_ARCH="${EXPECTED_ROCM_ARCH:-gfx950}"
 EXPECTED_WARP_SIZE="${EXPECTED_WARP_SIZE:-64}"

.ci/scripts/utils.sh

@@ -106,8 +106,8 @@ install_pytorch_and_domains() {
   local python_version=$(python -c 'import platform; v=platform.python_version_tuple(); print(f"{v[0]}{v[1]}")')
   local torch_release=$(cat version.txt)
   # Download key must match the upload key below (basename of dist/*.whl,
-  # which always carries setup.py's resolved +gitHASH). Branch-ref pins
-  # like `release/2.13` would otherwise produce `+gitrelease` here and
+  # which always carries the build's resolved +gitHASH). Branch-ref pins
+  # like `release/2.14` would otherwise produce `+gitrelease` here and
   # never hit the cache.
   local torch_short_hash=$(git rev-parse --short=7 HEAD)
   local torch_wheel_path="cached_artifacts/pytorch/executorch/pytorch_wheels/${system_name}/${python_version}"
@@ -127,18 +127,31 @@ install_pytorch_and_domains() {
   if [[ "${torch_wheel_not_found}" == "1" ]]; then
     echo "No cached wheel found, continue with building PyTorch at ${TORCH_VERSION}"
 
-    # Install PyTorch's own build-time deps so the source build does not
-    # silently inherit them from whatever else happens to be in the env
-    # (e.g. executorch's requirements-ci.txt).
-    pip install -r requirements-build.txt
     git submodule update --init --recursive
     if [[ "$(uname -m)" == "aarch64" ]]; then
       export BUILD_IGNORE_SVE_UNAVAILABLE=1
     fi
-    USE_DISTRIBUTED=1 python setup.py bdist_wheel
+    # PyTorch dropped setup.py. Build in a throwaway environment that can see the
+    # active one, so its build requirements, which pin a cmake that would be
+    # preferred over the one on PATH, cannot disturb what is installed here.
+    #
+    # Keep in sync with pytorch/pyproject.toml [build-system].requires.
+    local build_venv=/tmp/pytorch-build-venv
+    rm -rf "${build_venv}"
+    python -m venv --system-site-packages "${build_venv}"
+    "${build_venv}/bin/pip" install build "scikit-build-core>=1.0" ninja \
+      "packaging>=24.2" "typing-extensions>=4.10.0" pyyaml six numpy
+    USE_DISTRIBUTED=1 "${build_venv}/bin/python" -m build --wheel --no-isolation
+    rm -rf "${build_venv}"
     pip install "$(echo dist/*.whl)"
-
-    # Invariant: the basename setup.py just produced must match the cache
+    # A build with no BLAS succeeds silently, so check rather than assume.
+    (cd / && python -c "
+import torch
+assert torch._C.has_lapack, 'built without LAPACK'
+torch.linalg.qr(torch.randn(4, 4))
+")
+
+    # Invariant: the basename the build just produced must match the cache
     # URL we'd reconstruct on the next run. If they diverge (someone edits
     # torch_wheel_name above, or PyTorch renames its wheels), the cache
     # will silently miss and every macOS run will fall back to a ~30-min
@@ -178,7 +191,7 @@ install_pytorch_and_domains() {
   # Grab the pinned audio and vision commits from PyTorch
   TORCHAUDIO_VERSION=release/2.11
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.28
+  TORCHVISION_VERSION=release/0.29
   export TORCHVISION_VERSION
 
   install_domains

.ci/scripts/wheel/test_cpp_sdk.py

@@ -991,7 +991,7 @@ def test_every_shipped_header_compiles(work_dir: Path) -> None:
         # These say in their own text that they must not be included directly, and name the header to
         # include instead. Including one anyway is a use error rather than a packaging defect.
         "c10/util/complex_math.h",
-        "c10/util/complex_utils.h",
+        "torch/headeronly/util/complex_utils.h",
     )
 
     source = work_dir / "header_probe.cpp"

.github/workflows/rocm.yml

@@ -169,7 +169,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        rocm-version: ["7.1"]
+        rocm-version: ["7.2"]
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:
       id-token: write
@@ -206,7 +206,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        rocm-version: ["7.1"]
+        rocm-version: ["7.2"]
     with:
       timeout: 180
       no-sudo: true
@@ -248,7 +248,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        rocm-version: ["7.1"]
+        rocm-version: ["7.2"]
     with:
       timeout: 180
       no-sudo: true

.github/workflows/windows-msvc.yml

@@ -91,7 +91,7 @@ jobs:
 
       - name: Install build dependencies
         shell: pwsh
-        run: python -m pip install pyyaml torch==2.13.0 --extra-index-url https://download.pytorch.org/whl/test/cpu
+        run: python -m pip install pyyaml torch==2.14.0 --extra-index-url https://download.pytorch.org/whl/test/cpu
 
       - name: Build ExecuTorch
         shell: pwsh

backends/aoti/common_shims.cpp

@@ -159,6 +159,11 @@ AOTITorchError aoti_torch_get_numel(Tensor* tensor, int64_t* ret_numel) {
   return Error::Ok;
 }
 
+AOTITorchError aoti_torch_is_defined(Tensor* tensor, bool* ret_is_defined) {
+  *ret_is_defined = tensor != nullptr;
+  return Error::Ok;
+}
+
 // Device and layout utility functions
 int32_t aoti_torch_device_type_cpu() {
   // Let's say cpu is 0 for ET as well

backends/aoti/common_shims.h

@@ -62,6 +62,10 @@ aoti_torch_get_dim(Tensor* tensor, int64_t* ret_dim);
 AOTI_SHIM_EXPORT AOTITorchError
 aoti_torch_get_numel(Tensor* tensor, int64_t* ret_numel);
 
+// PyTorch has an undefined-tensor state with no equivalent here: null check.
+AOTI_SHIM_EXPORT AOTITorchError
+aoti_torch_is_defined(Tensor* tensor, bool* ret_is_defined);
+
 // Utility functions for device and layout information
 AOTI_SHIM_EXPORT int32_t aoti_torch_device_type_cpu();
 AOTI_SHIM_EXPORT int32_t aoti_torch_layout_strided();

backends/aoti/common_shims_slim.cpp

@@ -68,6 +68,14 @@ AOTITorchError aoti_torch_get_numel(Tensor* tensor, int64_t* ret_numel) {
   return Error::Ok;
 }
 
+AOTITorchError aoti_torch_is_defined(Tensor* tensor, bool* ret_is_defined) {
+  if (ret_is_defined == nullptr) {
+    return Error::InvalidArgument;
+  }
+  *ret_is_defined = tensor != nullptr && tensor->defined();
+  return Error::Ok;
+}
+
 int32_t aoti_torch_layout_strided() {
   // Slimtensor only support strided layout, the return value will always be 0,
   // a.k.a at::Layout::Strided;

backends/aoti/common_shims_slim.h

@@ -51,6 +51,10 @@ aoti_torch_get_dim(Tensor* tensor, int64_t* ret_dim);
 AOTI_SHIM_EXPORT AOTITorchError
 aoti_torch_get_numel(Tensor* tensor, int64_t* ret_numel);
 
+// Undefined means either a null handle or a tensor whose storage was released.
+AOTI_SHIM_EXPORT AOTITorchError
+aoti_torch_is_defined(Tensor* tensor, bool* ret_is_defined);
+
 AOTI_SHIM_EXPORT int32_t aoti_torch_layout_strided();
 
 // ============================================================

backends/apple/metal/metal_backend.py

@@ -32,16 +32,24 @@ def get_device_name(cls) -> str:
     @classmethod
     def get_supported_fallback_kernels(cls) -> Dict[str, Any]:
         return {
+            # An operator named the way it is registered also needs the name
+            # Inductor derives for it, so several appear under both.
             "aoti_torch_mps_addmm_out": None,
             "aoti_torch_mps_bmm_out": None,
             "aoti_torch_mps_convolution": None,
             "aoti_torch_mps_mm_out": None,
             "at::_ops::_scaled_dot_product_attention_math_for_mps::call": None,
+            "aoti_torch_mps__scaled_dot_product_attention_math_for_mps": None,
             "at::_ops::_scaled_dot_product_attention_math_for_mps_v2::call": None,
+            "aoti_torch_mps__scaled_dot_product_attention_math_for_mps_v2": None,
             "torchao::_linear_fp_act_4bit_weight": None,
+            "aoti_torch_mps__linear_fp_act_4bit_weight": None,
             "at::_ops::topk::call": None,
+            "aoti_torch_mps_topk": None,
             "metal::gather_qmv": None,
+            "aoti_torch_mps_gather_qmv": None,
             "metal::gated_delta_rule": None,
+            "aoti_torch_mps_gated_delta_rule": None,
         }
 
     @classmethod

backends/arm/test/misc/test_transpose_counts.py

@@ -543,7 +543,7 @@ def forward(self, x: torch.Tensor):
     "groupnorm_channels_last": TransposeCountCase(
         GroupNormModule(),
         (torch.randn(1, 4, 4, 4).to(memory_format=torch.channels_last),),
-        2,
+        1,
     ),
     "cumsum_rank4_dim3_channels_last": TransposeCountCase(
         CumsumModule(),

backends/cortex_m/test/misc/test_portable_int8.py

@@ -716,7 +716,10 @@ def _quantize_and_export(
     OP_CASES,
     xfails=xfails,
     strict=False,
-    skips={"while_loop": "Has been observed to hang randomly."},
+    skips={
+        "while_loop": "Has been observed to hang randomly.",
+        "dropout": "Not training, so it folds away and no node survives to carry int8.",
+    },
 )
 def test_shared_qspec_portable_int8_ops(op_case: OpCase) -> None:
     tester = CortexMTester(op_case.module, op_case.example_inputs)

backends/cortex_m/test/models/test_ds_cnn.py

@@ -15,22 +15,20 @@
     "executorch_exir_dialects_edge__ops_aten_linear_default": 1,
     "executorch_exir_dialects_edge__ops_aten_relu_default": 9,
     "executorch_exir_dialects_edge__ops_aten_view_copy_default": 1,
-    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default": 2,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_channel_default": 18,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default": 17,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default": 15,
 }
 
 ops_after_transforms: dict[str, int] = {
     "executorch_exir_dialects_edge__ops_aten_view_copy_default": 1,
-    "executorch_exir_dialects_edge__ops_cortex_m_dequantize_per_tensor_default": 1,
+    "executorch_exir_dialects_edge__ops_cortex_m_dequantize_per_tensor_default": 3,
     "executorch_exir_dialects_edge__ops_cortex_m_pad_default": 1,
-    "executorch_exir_dialects_edge__ops_cortex_m_quantize_per_tensor_default": 1,
+    "executorch_exir_dialects_edge__ops_cortex_m_quantize_per_tensor_default": 3,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_avg_pool2d_default": 1,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_conv2d_default": 4,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_depthwise_conv2d_default": 5,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_linear_default": 1,
-    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default": 2,
 }
 
 test_cases = {
@@ -43,11 +41,21 @@
 }
 
 
+ops_absent_after_transforms: list[str] = [
+    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default",
+]
+
+
 @parametrize("test_case", test_cases)
 def test_dialect_ds_cnn(test_case):
     inputs = test_case.get_example_inputs()
     tester = CortexMTester(test_case.model, inputs)
-    tester.test_dialect(ops_before_transforms, ops_after_transforms, qtol=1)
+    tester.test_dialect(
+        ops_before_transforms,
+        ops_after_transforms,
+        qtol=1,
+        ops_absent_after_transforms=ops_absent_after_transforms,
+    )
 
 
 @parametrize("test_case", test_cases)

backends/cortex_m/test/models/test_mobilenet_v2.py

@@ -20,22 +20,20 @@
     "executorch_exir_dialects_edge__ops_aten_hardtanh_default": 35,
     "executorch_exir_dialects_edge__ops_aten_linear_default": 1,
     "executorch_exir_dialects_edge__ops_aten_view_copy_default": 1,
-    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default": 1,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_channel_default": 104,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default": 79,
     "executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default": 67,
 }
 
 ops_after_transforms: dict[str, int] = {
     "executorch_exir_dialects_edge__ops_aten_view_copy_default": 1,
-    "executorch_exir_dialects_edge__ops_cortex_m_dequantize_per_tensor_default": 1,
-    "executorch_exir_dialects_edge__ops_cortex_m_quantize_per_tensor_default": 1,
+    "executorch_exir_dialects_edge__ops_cortex_m_dequantize_per_tensor_default": 2,
+    "executorch_exir_dialects_edge__ops_cortex_m_quantize_per_tensor_default": 2,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_add_default": 10,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_avg_pool2d_default": 1,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_conv2d_default": 35,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_depthwise_conv2d_default": 17,
     "executorch_exir_dialects_edge__ops_cortex_m_quantized_linear_default": 1,
-    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default": 1,
 }
 
 # Use larger sample set for calibration to get better quantization
@@ -54,6 +52,11 @@
 }
 
 
+ops_absent_after_transforms: list[str] = [
+    "executorch_exir_dialects_edge__ops_dim_order_ops__clone_dim_order_default",
+]
+
+
 @parametrize("test_case", test_cases)
 def test_dialect_mv2(test_case):
     inputs = test_case.get_example_inputs()
@@ -63,6 +66,7 @@ def test_dialect_mv2(test_case):
         ops_after_transforms,
         qtol=10,
         calibration_samples=calibration_samples,
+        ops_absent_after_transforms=ops_absent_after_transforms,
     )
 
     # assert that top 1 output matches

backends/cortex_m/test/tester.py

@@ -132,6 +132,7 @@ def test_dialect(
         qtol=0,
         atol=1e-03,
         calibration_samples=None,
+        ops_absent_after_transforms=None,
     ):
         """
         Test the python dialect op implementation.
@@ -142,13 +143,14 @@ def test_dialect(
             )
         else:
             quantization_stage = None
-
         self.quantize(quantization_stage)
         self.export()
         self.to_edge()
         self.check_count(ops_before_transforms)
         self.run_passes()
         self.check_count(ops_after_transforms)
+        if ops_absent_after_transforms:
+            self.check_not(ops_absent_after_transforms)
         self.run_method_and_compare_outputs(
             inputs=self.example_inputs, qtol=qtol, atol=atol
         )

backends/cuda/cuda_backend.py

@@ -669,7 +669,10 @@ def get_supported_fallback_kernels(cls) -> Dict[str, Any]:
             return {}
         return {
             "at::_ops::_weight_int4pack_mm::call": None,
+            # Also under the shim name Inductor derives for it.
+            "aoti_torch_cuda__weight_int4pack_mm": None,
             "at::_ops::sort_stable::call": None,
+            "aoti_torch_cuda_sort_stable": None,
             "aoti_torch_cuda_randint_low_out": None,
             "executorch_cuda::int4_plain_mm": None,
             "aoti_torch_cuda_int4_plain_mm": None,