llama.cpp: llama.cpp is an inference of several LLM models in C/C++
CVE-2026-34159 is fixed in llama.cpp on 1 platform by DEBIAN-CVE-2026-34159 (version 8611+dfsg-1), released April 1, 2026. It is not reported as exploited. Patch Radar priority: Urgent.
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.
Where it's fixed
| Product | Fixed in | Fix | Released |
|---|---|---|---|
| Linux | |||
| llama.cpp · Debian 14 | 8611+dfsg-1 | DEBIAN-CVE-2026-34159 | Apr 1, 2026 |
Patch Radar data is free to use with attribution. Terms and how to credit it.
Product names, logos and trademarks shown on Patch Radar belong to their respective owners. They are used only to identify the software each security fix applies to and to help readers find their platform. Their use does not imply any affiliation with, or endorsement by, those owners, and Patchblox is not affiliated with any of them.