Store layers in VRAM

ggml-cuda.h

@@ -14,6 +14,8 @@ void   ggml_cuda_mul_mat(const struct ggml_tensor * src0, const struct ggml_tens
 void * ggml_cuda_host_malloc(size_t size);
 void   ggml_cuda_host_free(void * ptr);
 
+void ggml_cuda_transform_tensor(struct ggml_tensor * tensor);
+
 #ifdef  __cplusplus
 }
 #endif