fix: reuse LlamaContext across batches to improve performance#40
Open
fix: reuse LlamaContext across batches to improve performance#40
Conversation
Previously, LlamaContext was recreated for every batch in embed_batch, causing significant overhead. This change refactors EmbeddingEngine to persist the context using a self-referential struct pattern (Box + transmute), ensuring context reuse while satisfying Rust's lifetime rules. Mutability propagation was also updated in dependent modules.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Refactors
EmbeddingEngineto reuseLlamaContextacrossembed_batchcalls instead of recreating it every time. This significantly reduces overhead for batch embedding operations.Changes
EmbeddingEngineto storeLlamaContextalongsideLlamaModelandLlamaBackend.Boxandunsafetransmute to handle the lifetime dependency betweenLlamaContextandLlamaModel.EmbeddingEngine::embed_batchto use the persistent context.ServerState,SearchEngine, andIndexerasllama_cpp_2::context::LlamaContextrequires mutable access for inference.Verification
cargo testto ensure all tests pass.Fixes #159