[cpu][perf] Accelerate unquantized-linear for AArch64 through oneDNN/ACL and weight prepack (#25948)

Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Fadi Arafeh
2025-10-04 12:16:38 +08:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent 2f7dbc9b42
commit 9705fba7b7
8 changed files with 111 additions and 16 deletions
+5
View File
@@ -205,6 +205,11 @@ class cmake_build_ext(build_ext):
# Make sure we use the nvcc from CUDA_HOME
if _is_cuda():
cmake_args += [f'-DCMAKE_CUDA_COMPILER={CUDA_HOME}/bin/nvcc']
other_cmake_args = os.environ.get("CMAKE_ARGS")
if other_cmake_args:
cmake_args += other_cmake_args.split()
subprocess.check_call(
['cmake', ext.cmake_lists_dir, *build_tool, *cmake_args],
cwd=self.build_temp)