From 9e04f2cb52fb5c2ea0f9406e8023f753cf3483fe Mon Sep 17 00:00:00 2001
From: slaren <slarengh@gmail.com>
Date: Fri, 4 Oct 2024 00:54:02 +0200
Subject: [PATCH] llama : print devices used on model load

---
 src/llama.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/llama.cpp b/src/llama.cpp
index 3a49ecffb2191a..9e83c79133478f 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -19100,8 +19100,13 @@ struct llama_model * llama_load_model_from_file(
 
             case GGML_BACKEND_DEVICE_TYPE_GPU:
             case GGML_BACKEND_DEVICE_TYPE_GPU_FULL:
+            {
+                size_t free, total; // NOLINT
+                ggml_backend_dev_memory(dev, &free, &total);
+                LLAMA_LOG_INFO("%s: using device %s (%s) - %zu MiB free\n", __func__, ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), free/1024/1024);
                 model->devices.push_back(dev);
                 break;
+            }
         }
     }