From 10dd6d0baf370d2040521f541f0ef13a57f45514 Mon Sep 17 00:00:00 2001
From: Junya Morioka <mjun@mjunya.com>
Date: Sun, 18 May 2025 02:45:41 +0900
Subject: [PATCH] update README.md

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 3a67f94..e6a4c43 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,10 @@ I also build and provide combinations of CUDA and PyTorch that are not officiall
 The building Github Actions Workflow can be found [here](./.github/workflows/build.yml).  
 The built packages are available on the [release page](https://github.com/mjun0812/flash-attention-prebuild-wheels/releases).
 
+This repository uses a self-hosted runner for building the wheels. If you find this project helpful, please consider supporting or sponsoring to help maintain the infrastructure.
+
+[![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/mjun0812)
+
 ## Install
 
 1. Select the versions for Python, CUDA, PyTorch, and flash_attn.