Skip to content

Fix safetensor overflow. - #4323

Draft
FeliGame wants to merge 5 commits into
ml-explore:mainfrom
FeliGame:fix-safetensor
Draft

Fix safetensor overflow.#4323
FeliGame wants to merge 5 commits into
ml-explore:mainfrom
FeliGame:fix-safetensor

Conversation

@FeliGame

Copy link
Copy Markdown
Contributor

Proposed changes

Fix 4244
enhance tensor bounds check and fix truncated std::accumulate.
WARNING: Current PR is addressed by Qwen3.6-35B-A3B MLX version (Running on M4 Pro locally), some of bound check might be redundant, let me check it twice.

Checklist

Put an x in the boxes that apply.

  • I have read the CONTRIBUTING document
  • I have run pre-commit run --all-files to format my code / installed pre-commit prior to committing changes
  • I have added tests that prove my fix is effective or that my feature works
  • I have updated the necessary documentation (if needed)

@FeliGame FeliGame changed the title FIx safetensor overflow. Fix safetensor overflow. Aug 17, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Heap out-of-bounds write in GGUF quantized tensor loading: allocation size truncates to 32 bits

1 participant