hardware_profile

Returns the cached system profile recorded by localLLM when the package was attached. The probe captures approximate CPU, RAM, and GPU capacity so that safety warnings can estimate whether a model fits the device.

Provides R bindings to the 'llama.cpp' library for running large language models.
The package uses a lightweight architecture where the C++ backend library is downloaded
at runtime rather than bundled with the package.
Package features include text generation, reproducible generation, and parallel inference.

Yaosheng Xu

localLLM

Running Local LLMs with 'llama.cpp' Backend

Eddie Yang

hardware_profile function

<dl><dt>refresh</dt>
<dd>When <code>TRUE</code>, forces a fresh probe instead of returning the cached profile.</dd></dl>

Arguments

Inspect detected hardware resources — hardware_profile

<dl>

<dt>refresh</dt>
<dd>When <code>TRUE</code>, forces a fresh probe instead of returning the cached profile.</dd>

</dl>

hardware_profile: Inspect detected hardware resources

Description

Usage

Value

Arguments

Examples