llama.cpp

c21a8964 - [CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871)

[CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871) * cann: fix ggml_backend_cann_buffer_get_tensor 1. fix data ptr offset 2. enable the acquisition of incomplete tensors * fix backend cann set_tensor