-
Couldn't load subscription status.
- Fork 700
Add top-level CMake backends target #12689
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.
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12689
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 4 PendingAs of commit f7d413f with merge base 37e3003 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
Vulkan build failure in the unittest job is real. Fixing that and then this should be good to land. |
Add a top level backends CMake target, which includes all configured backends. I validate this change by building a simple runner using the executorch_backends target and verifying that it was able to build and run an XNNPACK-delegated binary. Once the changes land in ExecuTorch, this will be long-term validated in executorch-examples CI.
To allow the executor runner target to use the executorch_backends target, I've also moved the Vulkan defs above the runner. This causes issues with the vulkan_executor_runner target, so I'm updating the main runner to include Vulkan and remove the Vulkan-specific one (subject to @SS-JIA's signoff).
This is done in the context of top-level CMake targets, tracked in #12293.