(2/6) Cache inference at do_inference - #95
Open
ErlisLushtaku wants to merge 9 commits into
Open
Conversation
Introduce PreparedModel and InferenceCache so full hits skip backend materialization, and wire one generate-and-judge path through content-addressed stores.
Keep only the lazy materialization fields needed for cache hits, and canonicalize inputs directly in do_inference.
Add short docstrings clarifying cache-identity preparation and miss-only backend materialization.
Handle only strings and LangChain chat prompt values used by current inference paths.
Remove silent cache fallbacks, share vLLM sampling defaults, and keep execution-only engine settings out of content descriptors.
Preserve the provenance required by the local store while keeping cache lookup and model materialization unchanged.
Replace role strings and conditionals with dedicated inference-cache subclasses while keeping SQLite persistence independent from inference orchestration.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Moves cache lookup and writes to
do_inference.PreparedModeldefers backend construction until an input misses the cache.This is stacked on #94.
Tests:
uv run pytest;uv run ruff check .;uv run ruff format --check ..