From a0e9f0a17a5deb933fef341e2c7b0131e4f83c8a Mon Sep 17 00:00:00 2001
From: Nick Stallons <88804918+nstallons@users.noreply.github.com>
Date: Wed, 24 Dec 2025 12:25:47 -0600
Subject: [PATCH] Update llama_cpp_install.md (#35)

Microsoft updated VS to 2026, CUDA only supports 2022.
---
 llama_cpp_install/llama_cpp_install.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/llama_cpp_install/llama_cpp_install.md b/llama_cpp_install/llama_cpp_install.md
index 38c925d..c4b7058 100644
--- a/llama_cpp_install/llama_cpp_install.md
+++ b/llama_cpp_install/llama_cpp_install.md
@@ -14,7 +14,7 @@ This guide helps you install `llama-cpp-python` with GPU (CUDA) support for Comf
 ### **2. Install Build Tools (If you haven't already)**
 
 * **Install Visual Studio Build Tools:**
-    * Download from [https://visualstudio.microsoft.com/downloads/](https://visualstudio.microsoft.com/downloads/) (under "Tools for Visual Studio").
+    * Download Visual Studio Build Tools 2022 [https://visualstudio.microsoft.com/downloads/](https://visualstudio.microsoft.com/downloads/](https://learn.microsoft.com/en-us/visualstudio/releases/2022/release-history#release-dates-and-build-numbers) (under 17.4 "Build Tools").
     * Run installer, select **"Desktop development with C++"** workload.
 * **Install NVIDIA CUDA Toolkit:**
     * Download your CUDA version (e.g., 12.6) from [https://developer.nvidia.com/cuda-toolkit-archive](https://developer.nvidia.com/cuda-toolkit-archive).
@@ -81,3 +81,4 @@ The script will:
 
 ---
 
+