mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-12 22:31:11 +04:00
Yash Raj PandeyandGitHub
f8def7fe16
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.