From c37785a275625b7e6778ad22f75b60537ec8c05f Mon Sep 17 00:00:00 2001
From: orlando <xiandao.airs@gmail.com>
Date: Mon, 26 Feb 2024 18:07:57 -0800
Subject: [PATCH] Update README.md

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

diff --git a/README.md b/README.md
index f1791556bf..276d02ef5d 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 <!-- markdownlint-disable MD033 -->
 <!-- markdownlint-disable MD004 -->
 <!-- markdownlint-disable MD029 -->
-# Pytorch 2.0.0 with Nvidia GPU on macOS
+# Pytorch 2.2.0 with Nvidia GPU on macOS
 --------------------------------------------------------------------------------
 [Features of pytorch 2.0](https://pytorch.org/blog/Accelerating-Hugging-Face-and-TIMM-models/) requires trions of [openAI triton](https://github.com/openai/triton), which needs NVIDIA GPUs (Compute Capability 7.0+, refer to https://developer.nvidia.com/cuda-gpus). In order to support the compilation via cuda, the hardware of eGPU needs to upgrade to 2080i +, like sales in [gaming box of 2080i](https://www.amazon.com/Embedded-Thunderbolt-Waterforce-Controller-Gv-N208TIXEB-11GC/dp/B07ZS9GZRY/ref=sr_1_5?crid=38RK3T5BAKIGN&keywords=gigabyte+gaming+box&qid=1679248280&s=pc&sprefix=gigabyte+gaming+box%2Ccomputers%2C147&sr=1-5).