feat: add lock to hf backend to prevent concurrent generation with conflicting weights #233
+559
−46
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
Merge ProtectionsYour pull request matches the following merge protections and will not be merged until they are valid. 🟢 Enforce conventional commitWonderful, this rule succeeded.Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/
|
jakelorocco
force-pushed
the
jal/hf-generation-lock
branch
3 times, most recently
from
4d1385f to
eb408e4
Compare
conflicting weights
jakelorocco
force-pushed
the
jal/hf-generation-lock
branch
from
eb408e4 to
8d8d683
Compare
| try: | ||
| # We can't know if adapters have been loaded / set previously. | ||
| # This call will throw an exception if none have been. | ||
| self.backend._model.set_adapter([]) |
Contributor
There was a problem hiding this comment.
https://huggingface.co/docs/transformers/en/peft
use disable_adapter instead
Contributor
Author
|
Closing this PR in favor of a simpler approach. Opening this issue to document future optimizations that can be done to speed up the generation lock for the local huggingface backend if needed. Will leave this branch un-deleted. If this code is used in the future, we should rename the HFGenerationLock and most of its fields for explainability and understanding. |
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Outdated suggestions cannot be applied.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.
Changes:
Testing: