ggml_soft_max_ext_inplace

Creates a graph node for extended softmax, modifying input tensor in place.
Returns a view of the input tensor.

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 

ggml_soft_max_ext_inplace function

<dl><dt>ctx</dt>
<dd>GGML context</dd>
<dt>a</dt>
<dd>Input tensor (typically attention scores)</dd>
<dt>mask</dt>
<dd>Optional attention mask tensor (F16 or F32). NULL for no mask.
Shape must be broadcastable to input tensor.</dd>
<dt>scale</dt>
<dd>Scaling factor, typically 1/sqrt(head_dim)</dd>
<dt>max_bias</dt>
<dd>Maximum ALiBi bias (0.0 to disable ALiBi)</dd></dl>

Arguments

Extended Softmax Inplace (Graph) — ggml_soft_max_ext_inplace

<dl>

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


<dt>a</dt>
<dd>Input tensor (typically attention scores)</dd>


<dt>mask</dt>
<dd>Optional attention mask tensor (F16 or F32). NULL for no mask.
Shape must be broadcastable to input tensor.</dd>


<dt>scale</dt>
<dd>Scaling factor, typically 1/sqrt(head_dim)</dd>


<dt>max_bias</dt>
<dd>Maximum ALiBi bias (0.0 to disable ALiBi)</dd>

</dl>

ggml_soft_max_ext_inplace: Extended Softmax Inplace (Graph)

Description

Usage

Value

Arguments

See Also