ggml_rope_multi: Multi-RoPE for Vision Models (Graph)

In ggmlR: 'GGML' Tensor Operations for Machine Learning

Multi-RoPE for Vision Models (Graph)

Description

Creates a graph node for multi-dimensional RoPE (MRoPE) used in vision transformers. Supports separate rotation for different positional dimensions (e.g., height, width, time).

Usage

ggml_rope_multi(
  ctx,
  a,
  b,
  c = NULL,
  n_dims,
  sections = c(0L, 0L, 0L, 0L),
  mode = 0L,
  n_ctx_orig = 0L,
  freq_base = 10000,
  freq_scale = 1,
  ext_factor = 0,
  attn_factor = 1,
  beta_fast = 32,
  beta_slow = 1
)

Arguments

ctx	GGML context
a	Input tensor
b	Position tensor (int32)
c	Optional frequency factors tensor (NULL for default)
n_dims	Number of dimensions to apply rotation to
sections	Integer vector of length 4 specifying dimension sections for MRoPE
mode	RoPE mode
n_ctx_orig	Original context length the model was trained on
freq_base	Base frequency for RoPE (default 10000 for most models)
freq_scale	Frequency scale factor (1.0 = no scaling)
ext_factor	YaRN extension factor (0.0 to disable)
attn_factor	Attention scale factor (typically 1.0)
beta_fast	YaRN parameter for fast dimensions
beta_slow	YaRN parameter for slow dimensions

Value

Tensor with multi-dimensional RoPE applied

See Also

Other rope: ggml_rope_ext_inplace(), ggml_rope_multi_inplace()

ggmlR documentation built on July 14, 2026, 1:08 a.m.