Add static module extension target #2904
Closed
Conversation
This file contains hidden or 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2904
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 45f80d8 with merge base 399482c ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
@GregoryComer has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
mikekgfb
approved these changes
Apr 6, 2024
|
@GregoryComer merged this pull request in fd26666. |
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Outdated suggestions cannot be applied.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.
Add an module extension target always built as a static library. This is a hacky workaround to the fact that the llama runner currently relies on some fragile linking behavior and requires consuming the module extension as a static lib. However, the nanogpt_runner needs to consume it as a static lib to avoid duplicate primitive op registration. I'm not 100% clear on why llama runner doesn't hit this yet. Maybe something to do with the primitive op -> executorch -> llama_runner -> llama_main chain having a top level target that doesn't reference the core executorch dependency leading to it not being pulled in at the top level?
Anyway, this new target will be removed once we refactor the CMake build post-alpha. Note that by adding a completely new target, this should cause no regressions and should be safe to land.