Skip to content

Llm preset cuda win #15253

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Llm preset cuda win #15253

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a4a1f24
no custom or quantized ops on win cuda
JacobSzwejbka Oct 18, 2025
8bbe392
lint
JacobSzwejbka Oct 18, 2025
505536d
just force them off
JacobSzwejbka Oct 18, 2025
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
7 changes: 6 additions & 1 deletion tools/cmake/preset/llm.cmake
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,12 @@ elseif(CMAKE_SYSTEM_NAME STREQUAL "Linux")
elseif(CMAKE_SYSTEM_NAME STREQUAL "Windows" OR CMAKE_SYSTEM_NAME STREQUAL
"WIN32"
)
# Windows or other OS-specific code here
# Windows-specific code: disable quantized and custom ops when building with
# CUDA
if(EXECUTORCH_BUILD_CUDA)
set(EXECUTORCH_BUILD_KERNELS_QUANTIZED OFF)
set(EXECUTORCH_BUILD_KERNELS_LLM OFF)
endif()
elseif(CMAKE_SYSTEM_NAME STREQUAL "Android")
# Android-specific code here
else()
Expand Down
Loading