Set encoder TP size to 1 by default #569
Merged
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
Edenzzzz
had a problem deploying
to
runpod-runners
GitHub Actions
Failure
Edenzzzz
had a problem deploying
to
runpod-runners
GitHub Actions
Failure
Edenzzzz
force-pushed
the
wenxuan/deprecate_tp
branch
from
8206640 to
53a6f4a
Compare
SolitaryThinker
approved these changes
Jul 9, 2025
SolitaryThinker
force-pushed
the
wenxuan/deprecate_tp
branch
from
53a6f4a to
4bca696
Compare
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Outdated suggestions cannot be applied.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.
After #594, encoder offload is enabled by default, so TP will almost always be slower than offload + layer-wise prefetch. This PR sets TP size to 1 for training and inference by default.
I will need to spend some time finishing up the LoRA features, so please ensure this doesn't break any training or inference scripts.
cc @BrianChen1129 @SolitaryThinker