quantize_nvfp4

Quantizes float data to NVFP4 format (NVIDIA FP4 with UE4M3 per-sub-block scale).

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

quantize_nvfp4 function

<dl><dt>src_data</dt>
<dd>Numeric vector of float values to quantize</dd>
<dt>n_rows</dt>
<dd>Number of rows</dd>
<dt>n_per_row</dt>
<dd>Number of elements per row (must be multiple of 64)</dd>
<dt>imatrix</dt>
<dd>Optional importance matrix (currently ignored)</dd></dl>

Arguments

Quantize Data (NVFP4) — quantize_nvfp4

<dl>

<dt>src_data</dt>
<dd>Numeric vector of float values to quantize</dd>


<dt>n_rows</dt>
<dd>Number of rows</dd>


<dt>n_per_row</dt>
<dd>Number of elements per row (must be multiple of 64)</dd>


<dt>imatrix</dt>
<dd>Optional importance matrix (currently ignored)</dd>

</dl>

quantize_nvfp4: Quantize Data (NVFP4)

Description

Usage

Value

Arguments

See Also