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Outdated suggestions cannot be applied.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
Implemented KVCacheAwareScorer which uses
kvcache.Indexer
as an embedded module.The latter is configured with default configuration + an env settable Redis server address, and a HuggingFace token which is an acceptable practice.
Changes:
Dockerfile
was changed:kvcache.Indexer
directly is having to statically link the HuggingFace Rust tokenizer's Go bindings.kvcache-manager
repo being internal, having Go download its modules requires configuring access. ThereforeGIT_NM_USER
andNM_TOKEN
have to be set.Makefile
'simage-build
target was slightly refactored and updated to support theDockerfile
changes, and building from nonamd64
archs.Follow-up work: