sycl: allow ggml-sycl configuration and compilation using Visual Studio project/solution #12625
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
documentation
sgeor255
approved these changes
Mar 28, 2025
qnixsynapse
approved these changes
Mar 28, 2025
There was a problem hiding this comment.
LGTM
The user can decide which compiler wants to use for the rest of llama.cpp, while ggml-sycl will always be compiled using the Intel official compiler.
This will only work when building ggml and its backend as shared libraries, i.e -DBUILD_SHARED_LIBS=ON.
For building as a single program/static library, -fsycl need to be added to C++ flags and the entire project should be built with the Intel SYCL compiler(icpx/icx).
|
Thank you for your feedback @qnixsynapse, I changed the documentation in 85e917d |
Rbiessy
reviewed
Mar 31, 2025
Co-authored-by: Svetlozar Georgiev <[email protected]>
Co-authored-by: Svetlozar Georgiev <[email protected]>
Merged 3rd and 4th point under only one point related to Visual Studio. Specify better how to build and use Visual Studio solution. Add note about tested configuration.
Rbiessy
reviewed
Apr 2, 2025
NeoZhangJianyu
approved these changes
Apr 2, 2025
|
Removing me from the review as you've already had plenty of feedback. Good Job! |
Rbiessy
approved these changes
Apr 4, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR enable the possibility of compiling and using llama.cpp with ggml-sycl backend as Visual Studio Project/Solution on windows.
The changes don't interfere with anything but the solution generation for ggml-sycl.
The user can decide which compiler wants to use for the rest of llama.cpp, while
ggml-syclwill always be compiled using the Intel official compiler.Tested current and new configurations on Windows 10 and Intel Arc B580