Bump PyTorch pin to 2.13

Author: JacobSzwejbka

.ci/docker/ci_commit_pins/pytorch.txt

@@ -1 +1 @@
-release/2.12
+release/2.13

.ci/docker/common/install_pytorch.sh

@@ -40,7 +40,7 @@ install_pytorch_and_domains() {
   # Grab the pinned audio and vision commits from PyTorch
   TORCHAUDIO_VERSION=release/2.11
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.27
+  TORCHVISION_VERSION=release/0.28
   export TORCHVISION_VERSION
 
   install_domains

.ci/scripts/utils.sh

@@ -107,7 +107,7 @@ install_pytorch_and_domains() {
   local torch_release=$(cat version.txt)
   # Download key must match the upload key below (basename of dist/*.whl,
   # which always carries setup.py's resolved +gitHASH). Branch-ref pins
-  # like `release/2.12` would otherwise produce `+gitrelease` here and
+  # like `release/2.13` would otherwise produce `+gitrelease` here and
   # never hit the cache.
   local torch_short_hash=$(git rev-parse --short=7 HEAD)
   local torch_wheel_path="cached_artifacts/pytorch/executorch/pytorch_wheels/${system_name}/${python_version}"
@@ -178,7 +178,7 @@ install_pytorch_and_domains() {
   # Grab the pinned audio and vision commits from PyTorch
   TORCHAUDIO_VERSION=release/2.11
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.27
+  TORCHVISION_VERSION=release/0.28
   export TORCHVISION_VERSION
 
   install_domains

install_requirements.py

@@ -15,6 +15,8 @@
 # The pip repository that hosts nightly torch packages.
 # This will be dynamically set based on CUDA availability and CUDA backend enabled/disabled.
 TORCH_URL_BASE = "https://download.pytorch.org/whl/test"
+TORCHAO_URL_BASE = "https://download.pytorch.org/whl/nightly"
+TORCHAO_NIGHTLY_VERSION = "0.18.0.dev20260715"
 
 # Since ExecuTorch often uses main-branch features of pytorch, only the nightly
 # pip versions will have the required features.
@@ -43,13 +45,19 @@ def install_requirements(use_pytorch_nightly):
 
     # Determine the appropriate PyTorch URL based on CUDA delegate status
     torch_url = determine_torch_url(TORCH_URL_BASE)
+    torchao_url = determine_torch_url(TORCHAO_URL_BASE)
 
     # pip packages needed by exir.
     TORCH_PACKAGE = [
         # Setting use_pytorch_nightly to false to test the pinned PyTorch commit. Note
         # that we don't need to set any version number there because they have already
         # been installed on CI before this step, so pip won't reinstall them
-        ("torch==2.12.0" if use_pytorch_nightly else "torch"),
+        ("torch==2.13.0" if use_pytorch_nightly else "torch"),
+        (
+            f"torchao=={TORCHAO_NIGHTLY_VERSION}"
+            if use_pytorch_nightly
+            else "torchao"
+        ),
     ]
 
     # Install the requirements for core ExecuTorch package.
@@ -66,44 +74,45 @@ def install_requirements(use_pytorch_nightly):
             *TORCH_PACKAGE,
             "--extra-index-url",
             torch_url,
+            "--extra-index-url",
+            torchao_url,
         ],
         check=True,
     )
 
-    LOCAL_REQUIREMENTS = [
-        "third-party/ao",  # We need the latest kernels for fast iteration, so not relying on pypi.
-    ] + (
+    LOCAL_REQUIREMENTS = (
         [
             "extension/llm/tokenizers",  # TODO(larryliu0820): Setup a pypi package for this.
         ]
         if sys.platform != "win32"
         else []
     )  # TODO(gjcomer): Re-enable when buildable on Windows.
 
-    # Install packages directly from local copy instead of pypi.
-    # This is usually not recommended.
-    new_env = os.environ.copy()
-    if ("EXECUTORCH_BUILD_KERNELS_TORCHAO" not in new_env) or (
-        new_env["EXECUTORCH_BUILD_KERNELS_TORCHAO"] == "0"
-    ):
-        new_env["USE_CPP"] = "0"
-    else:
-        assert new_env["EXECUTORCH_BUILD_KERNELS_TORCHAO"] == "1"
-        new_env["USE_CPP"] = "1"
-        new_env["CMAKE_POLICY_VERSION_MINIMUM"] = "3.5"
-    subprocess.run(
-        [
-            sys.executable,
-            "-m",
-            "pip",
-            "install",
-            # Without --no-build-isolation, setup.py can't find the torch module.
-            "--no-build-isolation",
-            *LOCAL_REQUIREMENTS,
-        ],
-        env=new_env,
-        check=True,
-    )
+    if LOCAL_REQUIREMENTS:
+        # Install packages directly from local copy instead of pypi.
+        # This is usually not recommended.
+        new_env = os.environ.copy()
+        if ("EXECUTORCH_BUILD_KERNELS_TORCHAO" not in new_env) or (
+            new_env["EXECUTORCH_BUILD_KERNELS_TORCHAO"] == "0"
+        ):
+            new_env["USE_CPP"] = "0"
+        else:
+            assert new_env["EXECUTORCH_BUILD_KERNELS_TORCHAO"] == "1"
+            new_env["USE_CPP"] = "1"
+            new_env["CMAKE_POLICY_VERSION_MINIMUM"] = "3.5"
+        subprocess.run(
+            [
+                sys.executable,
+                "-m",
+                "pip",
+                "install",
+                # Without --no-build-isolation, setup.py can't find the torch module.
+                "--no-build-isolation",
+                *LOCAL_REQUIREMENTS,
+            ],
+            env=new_env,
+            check=True,
+        )
 
 
 def install_optional_example_requirements(use_pytorch_nightly):
@@ -112,7 +121,7 @@ def install_optional_example_requirements(use_pytorch_nightly):
 
     print("Installing torch domain libraries")
     DOMAIN_LIBRARIES = [
-        ("torchvision==0.27.0" if use_pytorch_nightly else "torchvision"),
+        ("torchvision==0.28.0" if use_pytorch_nightly else "torchvision"),
         ("torchaudio==2.11.0" if use_pytorch_nightly else "torchaudio"),
     ]
     # Then install domain libraries

runtime/core/portable_type/c10/c10/util/BFloat16-math.h

@@ -181,7 +181,7 @@ template <
     typename T,
     typename std::enable_if_t<c10::is_reduced_floating_point_v<T>, int> = 0>
 inline T rsqrt(T a) {
-  return 1.0 / std::sqrt(float(a));
+  return 1.0f / std::sqrt(float(a));
 }
 template <
     typename T,

runtime/core/portable_type/c10/c10/util/complex_math.h

@@ -327,7 +327,7 @@ C10_HOST_DEVICE inline c10::complex<T> atanh(const c10::complex<T>& x) {
 template <typename T>
 C10_HOST_DEVICE inline c10::complex<T> log1p(const c10::complex<T>& z) {
 #if defined(__APPLE__) || defined(__MACOSX) || defined(__CUDACC__) || \
-    defined(__HIPCC__)
+    defined(__HIPCC__) || defined(__SYCL_DEVICE_ONLY__)
   // For Mac, the new implementation yielded a high relative error. Falling back
   // to the old version for now.
   // See https://github.com/numpy/numpy/pull/22611#issuecomment-1667945354

runtime/core/portable_type/c10/torch/headeronly/util/Half.h

@@ -236,7 +236,7 @@ C10_HOST_DEVICE inline float fp16_ieee_to_fp32_value(uint16_t h) {
   /*
    * - Choose either results of conversion of input as a normalized number, or
    * as a denormalized number, depending on the input exponent. The variable
-   * two_w contains input exponent in bits 27-31, therefore if its smaller than
+   * two_w contains input exponent in bits 27-31, therefore if it's smaller than
    * 2**27, the input is either a denormal number, or zero.
    * - Combine the result of conversion of exponent and mantissa with the sign
    * of the input number.

third-party/ao

@@ -1,2 +1,2 @@
-TORCH_VERSION = "2.12.0"
+TORCH_VERSION = "2.13.0"
 # NIGHTLY_VERSION = "dev20260318" Temporarily pinning to stable release candidate. Revert https://github.com/pytorch/executorch/pull/18287