ggml_task

A <code>ggml_task</code> is the contract object passed from the extraction layer to
the dispatch layer. It bundles the operation name, the dense feature matrix
(features in rows, cells in columns — the single-cell convention), the
operation parameters and the requested device. It performs no computation.

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_task function

<dl><dt>op</dt>
<dd>Operation name; must be registered in
<code>ggml_ops_registry</code> (e.g. <code>"embed"</code>).</dd>
<dt>matrix</dt>
<dd>A numeric <code>matrix</code> (dense) or <code>dgCMatrix</code> (sparse).
Rows are features (genes), columns are cells.</dd>
<dt>params</dt>
<dd>Named list of operation parameters (e.g. <code>n_components</code>).</dd>
<dt>device</dt>
<dd><code>"vulkan"</code>, <code>"cpu"</code> or <code>"auto"</code> (default).</dd></dl>

Arguments

Construct a single-cell compute task — ggml_task

<dl>

<dt>op</dt>
<dd>Operation name; must be registered in
<code>ggml_ops_registry</code> (e.g. <code>"embed"</code>).</dd>


<dt>matrix</dt>
<dd>A numeric <code>matrix</code> (dense) or <code>dgCMatrix</code> (sparse).
Rows are features (genes), columns are cells.</dd>


<dt>params</dt>
<dd>Named list of operation parameters (e.g. <code>n_components</code>).</dd>


<dt>device</dt>
<dd><code>"vulkan"</code>, <code>"cpu"</code> or <code>"auto"</code> (default).</dd>

</dl>

ggml_task: Construct a single-cell compute task

Description

Usage

Value

Arguments

See Also