-
Notifications
You must be signed in to change notification settings - Fork 428
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
Feat/Add a React Native LLaMA demo app for iOS #7134
Feat/Add a React Native LLaMA demo app for iOS #7134
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7134
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit f7aec5d with merge base a347665 (): NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@shoumikhin let me know if this is something that would be useful / any feedback on it. I know the Android side would be an useful thing to add but did not have time to look into it yet. |
Wow, this looks awesome @hietalajulius! |
@shoumikhin has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@pytorchbot label "topic: react native" |
Didn't find following labels among repository labels: topic: react native |
@hietalajulius do you think it's possible to add some info on t/s performance and model load time similar to the iOS app, maybe in a follow up PR? |
@pytorchbot label "release notes: react native llama demo app for ios" |
Didn't find following labels among repository labels: release notes: react native llama demo app for ios |
@pytorchbot label "topic: not user facing" |
@shoumikhin absolutely, let me add those + fix the linting 👍 |
@shoumikhin I added the model load time + tokens/sec info now (screen recording in PR description updated to showcase). The newlines that the linting was complaining about are also removed now, there does not seem to be a way to trigger the job on my end to make sure it passes but the errors were quite trivial. |
@shoumikhin has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@hietalajulius thanks for the update! |
@shoumikhin thanks! I should have taken a closer look at the contributing guide earlier, the |
@shoumikhin has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Hmm looks like still some permission issue with unittest-arm / linux-job, not entirely sure why |
Differential Revision: D66644092 Pull Request resolved: #7134
@hietalajulius many thanks again for the great contribution! Out internal vulnerability checker has flagged a potential threat from one of the dependencies, can please take a look?
Thanks! |
@shoumikhin thanks for the note! Let me check it out, looks like a transitive dependency of |
@shoumikhin I posted a PR here: #7218, let me know if that works 👍 |
Summary
rnllama.mov
Add React Native demo application for running LLaMA models
This PR introduces a new React Native mobile application demo that showcases running LLaMA language models on iOS devices using ExecuTorch. Key features include:
The demo app serves as a reference implementation for developers looking to integrate ExecuTorch and LLaMA models into React Native mobile applications. It complements the existing native iOS and Android demo apps by demonstrating cross-platform capabilities.
Release notes: examples
Test plan
Tested model initialization and chat functionality on: