Be able to set a max. number of GPUs to be used in split mode graph (#1051)

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

include/llama.h

@@ -362,6 +362,7 @@ extern "C" {
         // LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results
         // LLAMA_SPLIT_LAYER: ignored
         int32_t main_gpu;
+        int32_t max_gpu;
 
         // proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()
         const float * tensor_split;