mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-26 19:55:04 +00:00
* RoPE: fix back, CUDA support for back + noncont. * fix comments reg. non-cont. RoPE support [no-ci]
* RoPE: fix back, CUDA support for back + noncont. * fix comments reg. non-cont. RoPE support [no-ci]