ggml_win_part

Partitions a tensor into non-overlapping windows of size <code>w</code>.

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_win_part function

<dl><dt>ctx</dt>
<dd>GGML context</dd>
<dt>a</dt>
<dd>Input tensor</dd>
<dt>w</dt>
<dd>Window size</dd></dl>

Arguments

Window Partition (Graph) — ggml_win_part

<dl>

<dt>ctx</dt>
<dd>GGML context</dd>


<dt>a</dt>
<dd>Input tensor</dd>


<dt>w</dt>
<dd>Window size</dd>

</dl>

ggml_win_part: Window Partition (Graph)

Description

Usage

Value

Arguments