-
Notifications
You must be signed in to change notification settings - Fork 250
[Dist][Inference] U-haul TP and distribute utils code to TorchChat #873
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/torchchat/873
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ No FailuresAs of commit 8393020 with merge base b244612 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm - thanks for getting this started!
Summary: use_tp was renamed to use_distributed in #873, but the PR missed generate.py, which caused "AttributeError: 'BuilderArgs' object has no attribute 'use_tp'" when running generate with --profile.
This is a starting PR trying to uhaul some distributed related utils and TP code to torchchat from TorchTitan. The code most is gated and running
python3 torchchat.py chat llama3
still working. We will only develop in the distributed folder down the road. And this PR is an initial effort and we will have more PRs down the road.