fix(vram): contain malformed GGUF metadata - #11374
Open
richiejp wants to merge 1 commit into
Open
Conversation
Recover parser panics at metadata boundaries, skip unneeded remote arrays, and use the parser's overflow-hardened release. Keep detached gallery workers and CrispASR probes from terminating their processes on malformed GGUF input. Disable startup warming in the provided Compose files as an operational fallback. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR fixes a process-wide panic when gallery VRAM estimation encounters malformed remote GGUF metadata.
Notes for Reviewers
The background gallery VRAM warmer parses metadata from remote GGUF files. A malformed or transient range response can supply an impossible string length, causing gguf-parser-go to panic in a detached goroutine and terminate the LocalAI process. The estimator only needs architecture scalars, so parser failures now degrade to the existing size-only estimate and unnecessary tokenizer arrays are skipped.
Validation:
go test -count=1 ./pkg/vram ./core/gallery ./core/gallery/importers ./core/config ./backend/go/crispasrdocker compose -f docker-compose.yaml config --quietdocker compose -f docker-compose.distributed.yaml config --quietgit diff --checkRegression coverage includes valid remote GGUF metadata, overflowing tokenizer arrays, scalar string allocation panics, the detached gallery warmer, and malformed CrispASR metadata.
Related reports
Signed commits