Merge branch 'main' into coreml-dynamic-shape

Author: metascroy

.buckconfig

@@ -39,3 +39,6 @@
 
 [buck2]
 restarter=true
+
+[oss]
+folly_cxx_tests = False

.ci/scripts/gather_test_models.py

@@ -30,6 +30,7 @@
         "dl3": "linux.4xlarge.memory",
         "emformer_join": "linux.4xlarge.memory",
         "emformer_predict": "linux.4xlarge.memory",
+        "phi-4-mini": "linux.4xlarge.memory",
     }
 }
 

.ci/scripts/unittest-buck2.sh

@@ -8,13 +8,19 @@ set -eux
 
 # TODO: expand this to //...
 # TODO: can't query cadence & vulkan backends
+# TODO: can't query //kernels/prim_ops because of a cpp_unittest and
+# broken code in shim to read oss.folly_cxx_tests. Sending fix but it
+# needs to propagate and we need a submodule update.
 buck2 query "//backends/apple/... + //backends/example/... + \
 //backends/mediatek/... + //backends/test/... + //backends/transforms/... + \
-//backends/xnnpack/... + //configurations/... + //kernels/portable/cpu/... + \
-//runtime/... + //schema/... + //test/... + //util/..."
+//backends/xnnpack/... + //configurations/... + //kernels/aten/... + \
+//kernels/optimized/... + //kernels/portable/... + //kernels/quantized/... + \
+//kernels/test/... + //runtime/... + //schema/... + //test/... + //util/..."
 
+UNBUILDABLE_OPTIMIZED_OPS_REGEX="gelu|fft_r2c|log_softmax"
+BUILDABLE_OPTIMIZED_OPS=$(buck2 query //kernels/optimized/cpu/... | grep -E -v $UNBUILDABLE_OPTIMIZED_OPS_REGEX)
 # TODO: expand the covered scope of Buck targets.
 # //runtime/kernel/... is failing because //third-party:torchgen_files's shell script can't find python on PATH.
 # //runtime/test/... requires Python torch, which we don't have in our OSS buck setup.
-buck2 build //runtime/backend/... //runtime/core/... //runtime/executor: //runtime/kernel/... //runtime/platform/...
-buck2 test //runtime/backend/... //runtime/core/... //runtime/executor: //runtime/kernel/... //runtime/platform/...
+buck2 test $BUILDABLE_OPTIMIZED_OPS //kernels/portable/... //runtime/backend/... //runtime/core/... \
+      //runtime/executor: //runtime/kernel/... //runtime/platform/...

.github/workflows/build-wheels-m1.yml .github/workflows/build-wheels-macos.yml.github/workflows/build-wheels-m1.yml renamed to .github/workflows/build-wheels-macos.yml

@@ -1,11 +1,11 @@
 # From https://github.com/pytorch/test-infra/wiki/Using-Nova-Reusable-Build-Workflows
-name: Build M1 Wheels
+name: Build macOS Wheels
 
 on:
   pull_request:
     paths:
       - build/packaging/**
-      - .github/workflows/build-wheels-m1.yml
+      - .github/workflows/build-wheels-macos.yml
   push:
     branches:
       - nightly
@@ -56,7 +56,7 @@ jobs:
       # files to look at.
       submodules: true
       delocate-wheel: false
-      env-var-script: build/packaging/env_var_script_m1.sh
+      env-var-script: build/packaging/env_var_script_macos.sh
       pre-script: ${{ matrix.pre-script }}
       post-script: ${{ matrix.post-script }}
       package-name: ${{ matrix.package-name }}

.github/workflows/doc-build.yml

@@ -83,6 +83,7 @@ jobs:
         cp -rf docs/_build/html/* "${RUNNER_DOCS_DIR}"
 
         mv docs/_build/html "${RUNNER_ARTIFACT_DIR}"
+        cp -rf "${RUNNER_DOCS_DIR}"/javadoc "${RUNNER_ARTIFACT_DIR}"/html
 
         ls -R "${RUNNER_ARTIFACT_DIR}"/*/*.html
 

.lintrunner.toml

@@ -218,6 +218,8 @@ exclude_patterns = [
     'examples/**',
     'extension/**',
     'kernels/optimized/**',
+    # Justified <functional> include.
+    'runtime/kernel/thread_parallel_interface.h',
     'scripts/**',
     'third-party/**',
     'util/**',

CMakeLists.txt

@@ -751,7 +751,6 @@ if(EXECUTORCH_BUILD_PTHREADPOOL
    AND EXECUTORCH_BUILD_CPUINFO
 )
   add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/extension/threadpool)
-  add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/extension/parallel)
 endif()
 
 if(EXECUTORCH_BUILD_PYBIND)

CODEOWNERS

@@ -52,31 +52,31 @@
 /extension/export_util @kimishpatel
 /extension/flat_tensor @lucylq
 /extension/gguf_util @larryliu0820
-/extension/kernel_util @kimishpatel @manuelcandales
-/extension/llm @jackzhxng @iseeyuan @larryliu0820
-/extension/memory_allocator @JacobSzwejbka
+/extension/kernel_util @kimishpatel @manuelcandales @swolchok
+/extension/llm @jackzhxng @iseeyuan @larryliu0820 @swolchok
+/extension/memory_allocator @JacobSzwejbka @swolchok
 /extension/module @shoumikhin
-/extension/parallel @kimishpatel
+/extension/parallel @kimishpatel @swolchok
 /extension/pybindings @JacobSzwejbka @larryliu0820
-/extension/pytree @JacobSzwejbka
-# /extension/runner_util @dbort
+/extension/pytree @JacobSzwejbka @swolchok
+/extension/runner_util @swolchok
 /extension/tensor @shoumikhin
-# /extension/testing_util @dbort
-/extension/threadpool @kimishpatel
+/extension/testing_util @swolchok
+/extension/threadpool @kimishpatel @swolchok
 /extension/training @JacobSzwejbka
 
-/kernels @manuelcandales
+/kernels @manuelcandales @swolchok
 
 /profiler @tarun292 @Gasoonjia
 
-/runtime @JacobSzwejbka @lucylq
+/runtime @JacobSzwejbka @lucylq @swolchok
 /runtime/backend @cccclai
 
 /schema @JacobSzwejbka @lucylq
 
-/scripts @GregoryComer
+/scripts @GregoryComer @swolchok
 
-/shim @larryliu0820 @GregoryComer
+/shim @larryliu0820 @GregoryComer @swolchok
 
 /third-party @GregoryComer
 

Test.cmake

@@ -13,7 +13,6 @@ if(BUILD_TESTING)
   add_subdirectory(extension/evalue_util/test)
   add_subdirectory(extension/kernel_util/test)
   add_subdirectory(extension/memory_allocator/test)
-  add_subdirectory(extension/parallel/test)
   add_subdirectory(extension/pytree/test)
   add_subdirectory(kernels/portable/cpu/util/test)
   add_subdirectory(kernels/prim_ops/test)

backends/arm/operator_support/tosa_supported_operators.py

@@ -115,6 +115,7 @@ def is_node_supported(
             exir_ops.edge.aten.logical_and.default,
             exir_ops.edge.aten.logical_or.default,
             exir_ops.edge.aten.logical_xor.default,
+            exir_ops.edge.aten.logical_not.default,
             exir_ops.edge.aten.bitwise_and.Tensor,
             exir_ops.edge.aten.bitwise_or.Tensor,
             exir_ops.edge.aten.bitwise_xor.Tensor,
@@ -199,6 +200,7 @@ def is_node_supported(
                 exir_ops.edge.aten.logical_and.default,
                 exir_ops.edge.aten.logical_or.default,
                 exir_ops.edge.aten.logical_xor.default,
+                exir_ops.edge.aten.logical_not.default,
                 exir_ops.edge.aten.amax.default,
                 exir_ops.edge.aten.amin.default,
                 exir_ops.edge.aten.eq.Tensor,