CVE-2024-42479 llama.cpp allows write-what-where in rpc_server::set_tensor
CriticalCVSS 9.8
EPSS 2.6%
- Published
- Updated
- Exploit status
- No public exploit known
Description
llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address writing. This vulnerability is fixed in b3561.
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| ggerganov llama.cpp | = < b3561 | No fix listed |
| ggerganov llama.cpp | < b3561 | b3561 |
| ggml llama.cpp | < b3561 | b3561 |