Downloads · 30 days
11
7% of all-time downloads
gguf-iq3s-ubsan-shift-overflow-poc
AM-Core/gguf-iq3s-ubsan-shift-overflow-poc
gguf-iq3s-ubsan-shift-overflow-poc is a machine learning model from AM-Core. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Malformed GGUF PoC triggering sanitizer-fatal signed left-shift undefined behavior in llama.cpp / ggml IQ3S quantized dot-product path.
All-time downloads
157
Public
Repo size
8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.4 MB · 55%
At a glance
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 12, 2026
- SHA
- e69788c3
Model card
From the Hugging Face model README
GGUF IQ3_S UBSan signed left-shift overflow PoC
Malformed GGUF PoC triggering sanitizer-fatal signed left-shift undefined behavior in llama.cpp / ggml IQ3_S quantized dot-product path.
Summary
The GGUF file loads as GGUF v3 and reaches normal warmup/inference. During quantized CPU compute, it triggers UBSan in ggml_vec_dot_iq3_s_q8_K at quants.c:3314 / quants.c:3319.
This is not RCE. It is malformed model-file-triggered undefined behavior and denial-of-service risk.
Files
- m_00879_iq3s_ubsan_shift_overflow.gguf
- FINAL_HUNTR_FORM.md
- REPRO_COMMANDS.md
- llama_cli_fatal_ubsan.log
- llama_bench_fatal_ubsan.log
- SHA256SUMS.txt
- file_identity.txt
SHA256
2f365b71194eb48fdfda63abe3c8c8590d5e971ea5ced5b328c07ae4635a262c m_00879_iq3s_ubsan_shift_overflow.gguf
- Created
- May 12, 2026
- Updated
- May 12, 2026