Conversation
- revise docker run examples to name container and add cleanup - filter and format model list output with jq - add health check for llm service with http probe - include bonsai whitepaper link in references - move llama-server flags to sensible defaults; make context size optional - enable metrics collection
the old inject.rb manipulated oci blobs and json directly, which was fragile and made it hard to reason about correctness. little-surgery.rb delegates to umoci for all structural changes, handling only the staging and tarring that umoci can't do. this is both simpler and more maintainable. also adds umoci to the ci deps (alongside skopeo) and gates the packing target on linux, since rockcraft and umoci don't run on macos.
restructure the main flow to separate cached and download paths. replace the homegrown `die` function with `abort`. update comments to be more precise about what's actually happening -- the sha256 is huggingface's lfs oid, and the zero-length check catches failed curls. tweak little-surgery's comment about model-path to match.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
grab-bag of 1.7B tweaks that piled up together.