UPSTREAM PR #18432: android: fix infinite generation in shift_context() #729
+1
−0
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
When shift_context() discards tokens to free KV cache space, it decrements current_position but not stop_generation_position. This causes the termination check (current_position >= stop_generation_position) to never trigger, resulting in infinite text generation. Fix by also decrementing stop_generation_position by n_discard tokens. Fixes #18409
loci-dev
temporarily deployed
to
PROD__AL_DEMO
GitHub Actions
Inactive
|
Explore the complete analysis inside the Version Insights I've generated a summary report for your project. The analysis shows that Pull Request #729 for the llama.cpp repository (owned by auroralabs-loci) has no significant performance impact. Key findings:
The changes in this pull request maintain performance stability without introducing any performance regressions or bottlenecks. |
loci-dev
force-pushed
the
main
branch
2 times, most recently
from
8645b59 to
f2e8c7f
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Outdated suggestions cannot be applied.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.
Mirrored from ggml-org/llama.cpp#18432
Summary
Fixes #18409
When
shift_context()discards tokens to free KV cache space, it decrementscurrent_positionbut notstop_generation_position. This causes the termination check (current_position >= stop_generation_position) to never trigger, resulting in infinite text generation.Solution
Decrement
stop_generation_positionbyn_discardtokens alongsidecurrent_position.