From 42401c72b8d239240ed0fb37694d29ac33b3bc4f Mon Sep 17 00:00:00 2001
From: rankaiyx <rankaiyx@foxmail.com>
Date: Mon, 27 Apr 2026 20:31:13 +0800
Subject: [PATCH] Fix type casting for unaccounted memory calculation (#22424)

---
 common/fit.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/common/fit.cpp b/common/fit.cpp
index 4b95288907..aca3f4d407 100644
--- a/common/fit.cpp
+++ b/common/fit.cpp
@@ -856,7 +856,7 @@ void common_memory_breakdown_print(const struct llama_context * ctx) {
         ggml_backend_dev_memory(dev, &free, &total);
 
         const size_t self = mb.model + mb.context + mb.compute;
-        const size_t unaccounted = total - self - free;
+        const int64_t unaccounted = static_cast<int64_t>(total) - static_cast<int64_t>(free) - static_cast<int64_t>(self);
 
         table_data.push_back({
             template_gpu,
@@ -867,7 +867,7 @@ void common_memory_breakdown_print(const struct llama_context * ctx) {
             std::to_string(mb.model / MiB),
             std::to_string(mb.context / MiB),
             std::to_string(mb.compute / MiB),
-            std::to_string(unaccounted / MiB)});
+            std::to_string(unaccounted / static_cast<int64_t>(MiB))});
     }
 
     // print memory breakdown for host: