critical9.8
CVE-2026-34159
llama.cpp is an inference of several LLM models in C/C++.
Impact
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Ggml | Llama.Cpp | before b8492 |