From 6c9558ed04a6b64a84e27305294f5dc920e8ffb0 Mon Sep 17 00:00:00 2001
From: Ray Wang <raywang@nvidia.com>
Date: Fri, 18 Jul 2025 16:40:47 +0800
Subject: [PATCH] Update CUDA toolkits requirement (#128)

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 01e1f54..9e03fc6 100644
--- a/README.md
+++ b/README.md
@@ -46,7 +46,8 @@ Despite its lightweight design, DeepGEMM's performance matches or exceeds expert
 - Python 3.8 or higher
 - Compilers with C++20 support
 - CUDA Toolkit:
-    - CUDA 12.3 or higher for SM90
+    - Currently, CUDA 12.8 or higher is required, but support for older versions may be added in the future
+    - CUDA 12.8 or higher for SM90
         - **We highly recommend 12.9 or higher for the best performance**
     - CUDA 12.9 or higher for SM100
 - PyTorch 2.1 or higher