Debian/llama.cpp: critical 9.8
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 unauthenticat
Action: Upgrade llama.cpp to 8611+dfsg-1 or later.
Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 8611+dfsg-1 | - |
Fixed versions
| 8611+dfsg-1 |
Sources
published · modified · JSON