CVE-2024-42479
llama.cpp allows write-what-where in rpc_server::set_tensor
Summary
llama.cpp allows write-what-where in rpc_server::set_tensor
Original description
The description as published by the source.
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.
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
References
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com