GGUF tensor-offset out-of-bounds PoC

This repository hosts a benign security research PoC for a GGUF parser denial of service.

Files

  • gguf-huge-tensor-offset.gguf

Reproduction

Use latest gguf 0.19.0:

python3 -m venv .venv-gguf-019
. .venv-gguf-019/bin/activate
pip install gguf==0.19.0
python - <<'PY'
import gguf
gguf.GGUFReader("gguf-huge-tensor-offset.gguf")
PY

Observed result:

  • ValueError: cannot reshape array of size 0 into shape (1,)

The malformed file is only 160 bytes and patches the tensor offset_tensor field to 4294967296.

Safety note

This artifact is a non-executable malformed model-file PoC for parser-stress testing only.

Downloads last month
65
GGUF
Model size
1 params
Architecture
llama
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support