Fix prompt drop when input queue is not yet full at cache reset#484
Merged
Fix prompt drop when input queue is not yet full at cache reset#484
Conversation
When reset_cache and lora_scales are popped from self.parameters and the input queue doesn't yet have enough frames, the early return discards those values. On the next iteration init_cache defaults to False (pipeline already prepared), so the pipeline never resets its autoregressive cache and the new prompt has no visible effect from the user's perspective. Restore reset_cache and lora_scales into self.parameters before the early return so they are applied together with the new prompt once frames are available. Fixes #476 Co-Authored-By: Claude Sonnet 4.6 <[email protected]> Signed-off-by: Rafal Leszko <[email protected]>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When reset_cache and lora_scales are popped from self.parameters and the input queue doesn't yet have enough frames, the early return discards those values. On the next iteration init_cache defaults to False (pipeline already prepared), so the pipeline never resets its autoregressive cache and the new prompt has no visible effect from the user's perspective.
Restore reset_cache and lora_scales into self.parameters before the early return so they are applied together with the new prompt once frames are available.
Fixes #476