pytorch / pytorch/executorch

LLMs hallucinate with 4-bit quant group size 32, but not in ONNX

Open
#13,172 2 comments 0 reactions 1 assignee View on GitHub

@metascroy is already working on this.

Since Aug 7, 2025.

Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

🐛 Describe the bug

NA

Versions

NA

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.