llama : add log about loading model tensors (#11699)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 0487c978b5e77312a7e4e08322ba343a8b630302..e30db66e94643a309b9c66fef9ef4c7a5d8130ff 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1275,6 +1275,8 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
     const bool use_mmap_buffer = true;
 
+    LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, use_mmap_buffer ? "true" : "false");
+
     // build a list of buffer types for the CPU and GPU devices
     pimpl->cpu_buft_list = make_cpu_buft_list(devices);
     for (auto * dev : devices) {