ggml_flash_attn_ext_add_sinks: Attach Attention Sinks to a Flash-Attention Node
In ggmlR: 'GGML' Tensor Operations for Machine Learning
ggml_flash_attn_ext_add_sinks R Documentation
Attach Attention Sinks to a Flash-Attention Node
Description
Adds per-head "sink" logits, an always-available extra key that lets a query
attend to nothing in particular.
Usage
ggml_flash_attn_ext_add_sinks(tensor, sinks)
Arguments
tensor
A flash-attention node
sinks
Sink logits, one per head
Value
The tensor (for chaining)
See Also
ggml_soft_max_add_sinks
ggmlR documentation built on Oct. 23, 2026, 1:07 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
| ggml_flash_attn_ext_add_sinks | R Documentation |
Attach Attention Sinks to a Flash-Attention Node
Description
Adds per-head "sink" logits, an always-available extra key that lets a query attend to nothing in particular.
Usage
ggml_flash_attn_ext_add_sinks(tensor, sinks)
Arguments
tensor |
A flash-attention node |
sinks |
Sink logits, one per head |
Value
The tensor (for chaining)
See Also
ggml_soft_max_add_sinks
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.