-
Notifications
You must be signed in to change notification settings - Fork 324
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
Add example of LLava encoder #2375
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2375
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit ec64e19 with merge base 75284d2 (): NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D54812717 |
Summary: For some models where the grad is enabled (like LLava model), we need to disable grad before exporting. This PR is to add this guard when using export script. It would not affect the models that grad is not enabled. Reviewed By: cccclai Differential Revision: D54812718
Summary: Add the example to start enabling LLava, one multimodal model in generative AI area. In this example, we initiate the process of running LLava through ExecuTorch. Refer to the added README.md for details. Reviewed By: cccclai Differential Revision: D54812717
This pull request was exported from Phabricator. Differential Revision: D54812717 |
This pull request has been merged in 42eeebc. |
The doc build job looks fixed in trunk now I think https://hud.pytorch.org/hud/pytorch/executorch/main, so we should be good there. For this PR, doing a rebase will fix the doc build failure. On the other hand, let me retry those remaining failures in trunks, some of them look flaky. |
This pull request has been reverted by 3e414fb. |
Summary: Add the example to start enabling LLava, one multimodal model in generative AI area. In this example, we initiate the process of running LLava through ExecuTorch. Refer to the added README.md for details.
Differential Revision: D54812717