Fedora 40: llama-cpp 2024-b07b0b41ec Security Advisory Updates
fedora
November 5, 2024
Update to b3561
Summary
The main goal of llama.cpp is to run the LLaMA model using 4-bit
integer quantization on a MacBook
* Plain C/C++ implementation without dependencies
* Apple silicon first-class citizen - optimized via ARM NEON, Accelerate
and Metal frameworks
* AVX, AVX2 and AVX512 support for x86 architectures
* Mixed F16 / F32 precision
* 2-bit, 3-bit, 4-bit, 5-bit, 6-bit and 8-bit integer quantization support
* CUDA, Metal and OpenCL GPU backend support
The original implementation of llama.cpp was hacked in an evening.
Since then, the project has improved significantly thanks to many
contributions. This project is mainly for educational purposes and
serves as the main playground for developing new features for the
ggml library.
Update Information:
Update to b3561
Topics Covered
Change Log
* Sat Oct 26 2024 Tom Rix
References
[ 1 ] Bug #2304712 - CVE-2024-42479 llama-cpp: Write-what-where in rpc_server::set_tensor [fedora-all]
https://bugzilla.redhat.com/show_bug.cgi?id=2304712
Update Instructions
This update can be installed with the "dnf" update program. Use su -c 'dnf upgrade --advisory FEDORA-2024-b07b0b41ec' at the command line. For more information, refer to the dnf documentation available at http://dnf.readthedocs.io/en/latest/command_ref.html#upgrade-command-label
PREVIOUS
NEXT
Severity
important
Lowest
Low
Medium
High
Critical
Name: llama-cpp
Product: Fedora 40
Version: b3561
Release: 1.fc40
Summary: Port of Facebook's LLaMA model in C/C++
Topics Covered
Get the latest News and Insights
Get the latest Linux and open source security news straight to your inbox.
Related News
Powered By
Linux Security - Your source for Top Linux News, Advisories, HOWTOs and Feature Releases
QUICK LINKS
subscribe to newsletters!
Like staying secure? So do we.
Sign up for updates, tips, and alerts!