Upgrade llama.cpp b8648 → b8664; expose KV cache idle-eviction API#71
Merged
bernardladenthin merged 1 commit intomasterfrom Apr 4, 2026
Merged
Conversation
Version bump: - CMakeLists.txt GIT_TAG b8648 → b8664 - README.md llama.cpp badge and link updated - CLAUDE.md pinned version updated - README.md Java badge corrected from 11+ to 8+ (pom.xml already targets 1.8) New ModelParameters setters (all three work together to enable idle-slot eviction, a b8664 feature that saves KV state of idle slots to RAM and restores on cache-hit, freeing GPU memory between requests): - setKvUnified(boolean) → --kv-unified / --no-kv-unified - setCacheRamMib(int) → --cache-ram N (MiB; -1=unlimited, 0=disabled) - setClearIdle(boolean) → --clear-idle / --no-clear-idle (new in b8664) Both boolean setters remove the opposite flag so flip calls are safe. All three are covered by 13 new unit tests in ModelParametersExtendedTest. https://claude.ai/code/session_01UqHGktHkNpEri7QLZE5cjr
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Version bump:
New ModelParameters setters (all three work together to enable idle-slot eviction, a b8664 feature that saves KV state of idle slots to RAM and restores on cache-hit, freeing GPU memory between requests):
Both boolean setters remove the opposite flag so flip calls are safe. All three are covered by 13 new unit tests in ModelParametersExtendedTest.
https://claude.ai/code/session_01UqHGktHkNpEri7QLZE5cjr