Debian/llama.cpp: critical 9.8
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints with
Action: Upgrade llama.cpp to 7593+dfsg-1 or later.
Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 7593+dfsg-1 | - |
Fixed versions
| 7593+dfsg-1 |
Sources
published · modified · JSON