kv-cache : support layer reuse #15504
Merged
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
qnixsynapse
pushed a commit
to menloresearch/llama.cpp
that referenced
this pull request
Aug 25, 2025
* kv-cache : support layer reuse ggml-ci * cont : update comments [no ci]
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Outdated suggestions cannot be applied.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.
The logic for KV cache layer reuse was hacked quickly for the Gemma-3n release. This PR refactors the implementation to provide more generic support for this functionality.
llama_memory_i::layer_reuse_cbsimilar tollama_memory_i::layer_filter_cbbool hparams.has_kv(il)llama_kv_cache