Update upstream PR reference for slot_prompt_similarity setter#99
Merged
bernardladenthin merged 1 commit intomasterfrom Apr 28, 2026
Merged
Update upstream PR reference for slot_prompt_similarity setter#99bernardladenthin merged 1 commit intomasterfrom
bernardladenthin merged 1 commit intomasterfrom
Conversation
The patch proposal has been submitted upstream as ggml-org/llama.cpp#22393 so the local tracking file is no longer needed. - Delete llama-cpp.patch.md - REFACTORING.md forward-references section: replace file reference with the actual PR URL - 49be664_24918e4.md documentation table: mark file deleted, add PR link - jllama.cpp configureParallelInference comment: replace "see llama-cpp.patch.md" with the PR URL https://claude.ai/code/session_01C9wNVhq6d4eK97g6hsabcC
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This change updates documentation and code comments to reference the upstream llama.cpp PR that adds runtime mutation support for the
slot_prompt_similaritythreshold, replacing the local patch documentation with a direct link to the merged upstream change.Key Changes
Removed
llama-cpp.patch.md: Deleted the tracked artefact document that proposed a patch for upstream llama.cpp. This patch has now been merged upstream as PR ggml-org/llama.cpp#22393.Updated
src/main/cpp/jllama.cpp: Modified the comment block inconfigureParallelInferenceto reference the actual upstream PR URL instead of the local patch file. The comment now points tohttps://github.com/ggml-org/llama.cpp/pull/22393and clarifies that the upstream setter will be available once the llama.cpp pin is bumped past b8913.Updated
REFACTORING.md: Changed the "Forward references" section to link directly to the upstream PR instead of referencing the localllama-cpp.patch.mdfile. This clarifies that the feature is now tracked upstream rather than as a local proposal.Updated
49be664_24918e4.md: Minor documentation update reflecting the removal of the patch file.Implementation Details
The actual functionality (getter/setter for
slot_prompt_similarity) remains unchanged and will be available once:configureParallelInferenceis uncommentedNo behavioral changes in this commit; this is purely documentation and reference cleanup to track the upstream work.
https://claude.ai/code/session_01C9wNVhq6d4eK97g6hsabcC