fix: remove stale num_return_sequences warning in paged generate#45565
Closed
armorbreak001 wants to merge 1 commit intohuggingface:mainfrom
Closed
fix: remove stale num_return_sequences warning in paged generate#45565armorbreak001 wants to merge 1 commit intohuggingface:mainfrom
armorbreak001 wants to merge 1 commit intohuggingface:mainfrom
Conversation
The continuous batching path already handles num_return_sequences by expanding requests in generate_batch(). The warning about it being unsupported is stale and misleading. Keep the warning for num_beams > 1 which is still not supported. Also use the prepared generation config to read num_beams instead of raw kwargs, and cache it to avoid calling _prepare_generation_config twice.
Contributor
|
This PR was flagged by our automated quality checks. If you're a genuine Common reasons for flagging:
We appreciate your contribution and apologize if this is a false positive! |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The
generate(..., cache_implementation="paged")path emits a misleading warning thatnum_return_sequencesis not supported for continuous batching. This is stale —generate_batch()already handlesnum_return_sequencesby expanding the number of requests internally.Changes
num_return_sequences > 1condition from the warning checknum_beams > 1(still not supported)num_beamsfrom the prepared generation config instead of raw kwargs (more accurate)_prepare_generation_config()twiceBefore
After (when num_beams=1)
No warning emitted.
After (when num_beams > 1)
Fixes #45563