Skip to content

Enable cpp kernel building #2402

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 19, 2025
Merged

Enable cpp kernel building #2402

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 14 additions & 13 deletions setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -385,19 +385,20 @@ def get_extensions():
extra_compile_args["cxx"].extend(
["-O3" if not debug_mode else "-O0", "-fdiagnostics-color=always"]
)

# TODO(future PR): make this work without using `TORCH_VERSION_AT_LEAST_2_7`,
# because we should not be using anything from `torchao` to build `torchao`.
# if use_cpu_kernels and is_linux and TORCH_VERSION_AT_LEAST_2_7:
# if torch._C._cpu._is_avx512_supported():
# extra_compile_args["cxx"].extend(
# [
# "-DCPU_CAPABILITY_AVX512",
# "-march=native",
# "-mfma",
# "-fopenmp",
# ]
# )
if (
use_cpu_kernels
and is_linux
and hasattr(torch._C._cpu, "_is_avx512_supported")
and torch._C._cpu._is_avx512_supported()
):
extra_compile_args["cxx"].extend(
[
"-DCPU_CAPABILITY_AVX512",
"-march=native",
"-mfma",
"-fopenmp",
]
)

if debug_mode:
extra_compile_args["cxx"].append("-g")
Expand Down
Loading