nn_gru_step

internal

Provides 'R' bindings to the 'GGML' tensor library for machine
learning, designed primarily for 'Vulkan' GPU acceleration with full CPU
fallback. 'Vulkan' support is auto-detected at build time on Linux (when
'libvulkan-dev' and 'glslc' are installed) and on Windows (when 'Vulkan'
'SDK' is installed and 'VULKAN_SDK' environment variable is set); all
operations fall back to CPU transparently when no GPU is available.
Implements tensor operations, neural network layers, quantization, and a
'Keras'-like sequential model API for building and training networks.
Includes 'AdamW' (Adam with Weight decay) and 'SGD' (Stochastic Gradient
Descent) optimizers with 'MSE' (Mean Squared Error) and cross-entropy
losses. Also provides a dynamic 'autograd' engine ('PyTorch'-style) with
data-parallel training via 'dp_train()', broadcast arithmetic, 'f16'
(half-precision) support on 'Vulkan' GPU, and a multi-head attention layer
for building Transformer architectures. Serves as backend for 'LLM' (Large
Language Model) inference via 'llamaR' and Stable Diffusion image
generation via 'sdR'. See <https://github.com/ggml-org/ggml> for more
information about the underlying library.

Yuri Baramykov

ggmlR

'GGML' Tensor Operations for Machine Learning

Georgi Gerganov

Jeffrey Quesnelle

Bowen Peng

Mozilla Foundation 

nn_gru_step function

<dl><dt>ctx</dt>
<dd>ggml compute context</dd>
<dt>x_t</dt>
<dd>Input at this step: [input_size, N]</dd>
<dt>h_t</dt>
<dd>Previous hidden state: [units, N]</dd>
<dt>W_zh</dt>
<dd>[input_size, 2*units]</dd>
<dt>U_zh</dt>
<dd>[units, 2*units]</dd>
<dt>b_zh</dt>
<dd>[2*units]</dd>
<dt>W_n</dt>
<dd>[input_size, units]</dd>
<dt>U_n</dt>
<dd>[units, units]</dd>
<dt>b_n</dt>
<dd>[units]</dd>
<dt>units</dt>
<dd>Integer</dd>
<dt>act_cell</dt>
<dd>Activation for candidate (tanh)</dd>
<dt>act_rec</dt>
<dd>Activation for z/r gates (sigmoid)</dd></dl>

Arguments

Build one GRU step — nn_gru_step

<dl>

<dt>ctx</dt>
<dd>ggml compute context</dd>


<dt>x_t</dt>
<dd>Input at this step: [input_size, N]</dd>


<dt>h_t</dt>
<dd>Previous hidden state: [units, N]</dd>


<dt>W_zh</dt>
<dd>[input_size, 2*units]</dd>


<dt>U_zh</dt>
<dd>[units, 2*units]</dd>


<dt>b_zh</dt>
<dd>[2*units]</dd>


<dt>W_n</dt>
<dd>[input_size, units]</dd>


<dt>U_n</dt>
<dd>[units, units]</dd>


<dt>b_n</dt>
<dd>[units]</dd>


<dt>units</dt>
<dd>Integer</dd>


<dt>act_cell</dt>
<dd>Activation for candidate (tanh)</dd>


<dt>act_rec</dt>
<dd>Activation for z/r gates (sigmoid)</dd>

</dl>

Build one GRU step

nn_gru_step: Build one GRU step

Description

Usage

Value

Arguments