llama: model_loader: add TENSOR_READ_LAZY (#27794)

* llama: model_loader: add TENSOR_GET_ROW_LAZY

* add --tensor-read-lazy

* rename to TENSOR_READ_LAZY

* gen docs

* address comments

common/common.h

@@ -483,6 +483,8 @@ struct common_params {
     enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs
     enum llama_load_mode  load_mode  = LLAMA_LOAD_MODE_AUTO; // how to load the model
 
+    enum llama_tensor_read_lazy tensor_read_lazy = LLAMA_TENSOR_READ_LAZY_AUTO; // on-demand reading of tensors marked by the arch
+
     common_cpu_params cpuparams;
     common_cpu_params cpuparams_batch;