Skip to content

Commit 69e2672

Browse files
author
Github Executorch
committed
Update on "Use c10 version of half/bfloat16 in executorch"
Accomplished by importing relevant files from c10 into executorch/runtime/core/portable_type/c10, and then using `using` in the top-level ExecuTorch headers. This approach should keep the ExecuTorch build hermetic for embedded use cases. In the future, we should add a CI job to ensure the c10 files stay identical to the PyTorch ones. Differential Revision: [D66106969](https://our.internmc.facebook.com/intern/diff/D66106969/) [ghstack-poisoned]
2 parents ef0e952 + 351e65f commit 69e2672

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

backends/apple/coreml/CMakeLists.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -135,7 +135,7 @@ target_include_directories(
135135
)
136136
target_include_directories(coremldelegate PRIVATE ${EXECUTORCH_ROOT}/..)
137137
target_include_directories(coremldelegate PRIVATE ${EXECUTORCH_ROOT}/runtime/core/portable_type)
138-
target_compile_definitions(coremldelegate C10_USING_CUSTOM_GENERATED_MACROS)
138+
target_compile_definitions(coremldelegate PRIVATE C10_USING_CUSTOM_GENERATED_MACROS)
139139
target_link_libraries(coremldelegate PRIVATE executorch_core)
140140

141141
if(EXECUTORCH_BUILD_DEVTOOLS)

0 commit comments

Comments
 (0)