ggml-org/llama.cpp b10353

on GitHub

ggml : require contiguous src for ROLL on CUDA and Metal (#25928)

ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a
valid input, but the CUDA and Metal roll kernels index by ne alone and
never read the nb strides. A non-contiguous src therefore produced
silently wrong results. Neither backend declared a contiguity
requirement in supports_op, so the scheduler did not fall back to the
CPU implementation, which does handle strides correctly.

Add the requirement to both backends, matching the existing
GGML_OP_ROPE guard, and add a permuted test_roll case.