openRuyi Lookout
← Packages

llama-cpp

LLM inference in C/C++

Current
0.4.1
Candidate
CheckFailed
Comparison
Cannot compare current observations
License
MIT AND Apache-2.0 AND Unlicense

Build

TargetResultLast successful versionSucceeded at
rva23llama-cpp
0.4.1
rva23llama-cpp:rocm
0.4.1
rva20llama-cpp
b10448
rva20llama-cpp:rocm
b10448
x86_64llama-cpp
0.4.1
x86_64llama-cpp:rocm
0.4.1

Advisory · 7

Query ecosystem
GITOSV
Query name
https://github.com/ggml-org/llama.cppOSV
Query version
v0.4.1OSV

Provider matches do not establish RPM applicability. Local patches, bundled dependencies and binary artifacts are not evaluated.

Description

llama.cpp provides performant inference for large language models in plain C/C++. This package includes command-line tools, a server, and shared libraries.

Changelog

PR · 3

Checks
MonitorObservationLast checked
Stale
Repository refresh: git fetch exited 128 (authentication)
CheckFailed
nvchecker reported no usable result
Source last confirmed at 2026-11-10T17:23:44+00:00; repository refresh overdue.
Last attempted
Checked
Checked
Not configured
No reliable monitor identity/configuration.
—
Not configured
No reliable monitor identity/configuration.
—
Not configured
No reliable monitor identity/configuration.
—
Checked
Repository query; subpackage and local-patch applicability are not evaluated.
Last attempted
Not configured
No reliable monitor identity/configuration.
—