mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
* ggml : add graph tensor allocator * ggml : don't calculate data pointer of unallocated tensors when creating a view with an offset * ggml : refactor ggml_view_Nd into ggml_view_tensor_offset
653 B
653 B