ggml_run

Validates a <code>ggml_task</code> against <code>ggml_ops_registry</code>,
resolves the compute device, invokes the registered engine and returns a
<code>ggml_result</code>. This is the dispatch layer: the only place that
decides GPU vs CPU. <code>device = "auto"</code> (the task default) uses Vulkan when
a GPU is available and CPU otherwise; <code>device = "vulkan"</code> on a machine
with no GPU degrades to CPU with a message rather than failing.

Provides 'R' bindings to the 'GGML' tensor library for machine
learning, optimized for 'Vulkan' GPU acceleration with a transparent CPU
fallback. The package features a 'Keras'-like sequential API and a
'PyTorch'-style 'autograd' engine for building, training, and deploying
neural networks. Key capabilities include high-performance 5D tensor
operations, 'f16' precision, and efficient quantization. It supports
native 'ONNX' model import (50+ operators) and 'GGUF' weight loading
from the 'llama.cpp' and 'Hugging Face' ecosystems. Designed for
zero-overhead inference via dedicated weight buffering, it integrates
seamlessly as a 'parsnip' engine for 'tidymodels' and provides
first-class learners for the 'mlr3' framework.
See <https://github.com/ggml-org/ggml> for more information about the
underlying library.

Yuri Baramykov

ggmlR

'GGML' Tensor Operations for Machine Learning

ggml_run function

<dl><dt>task</dt>
<dd>A <code>ggml_task</code>.</dd>
<dt>backend</dt>
<dd>Optional override of <code>task$device</code>:
<code>"auto"</code> (default), <code>"vulkan"</code> or <code>"cpu"</code>.</dd>
<dt>...</dt>
<dd>Additional parameters merged over <code>task$params</code> and passed to
the engine.</dd></dl>

Arguments

Run a single-cell task on the GGML backend — ggml_run

<dl>

<dt>task</dt>
<dd>A <code>ggml_task</code>.</dd>


<dt>backend</dt>
<dd>Optional override of <code>task$device</code>:
<code>"auto"</code> (default), <code>"vulkan"</code> or <code>"cpu"</code>.</dd>


<dt>...</dt>
<dd>Additional parameters merged over <code>task$params</code> and passed to
the engine.</dd>

</dl>

ggml_run: Run a single-cell task on the GGML backend

Description

Usage

Value

Arguments

See Also