CVE-2026-116829 llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
- Exploited in the wild
- Not known
- Fix
- Available
What is CVE-2026-116829?
CVE-2026-116829 is a medium-severity vulnerability in ggml-org llama.cpp, published on 27 Oct 2026.
Official description
llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.
Weakness: CWE-190
Which versions are affected by CVE-2026-116829?
How do I fix CVE-2026-116829?
Upgrade to a fixed version.
Is CVE-2026-116829 being exploited?
There is no known exploitation of CVE-2026-116829 in the wild and no public exploit code.
Sources
Also known as DEBIAN-CVE-2026-116829, GHSA-3jhp-qv93-3428, UBUNTU-CVE-2026-116829.