-
Notifications
You must be signed in to change notification settings - Fork 607
Android refactor cmake build #5204
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
Instead, in Java layer, add a note that if no args is given to forward, we will infer that the user wants to try with sample value
Instead, if we pass no args to forward(), we infer that the user wants to test against default inputs (ones) so we prepare the inputs for user
…into experiments-jni
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5204
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 957d1f1 with merge base 2863536 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
The failed job seems relevant to this refactoring |
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Fixed the issue |
libexecutorch.so
. Note that by default (our CI server) we always build LLM as well. LLM is "a plugin" to the original JNI. It has minimal size impact. Users can disable it with-DEXECUTORCH_BUILD_LLAMA_JNI=OFF
if they absolutely don't need it.