From 4d0d0a4dee8d5d44e7ead733af63a2d0e22a83cc Mon Sep 17 00:00:00 2001
From: josc146 <josStorer@outlook.com>
Date: Tue, 23 May 2023 20:52:18 +0800
Subject: [PATCH] update readme

---
 README.md    | 2 ++
 README_ZH.md | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/README.md b/README.md
index f263b6c..f1c801c 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,8 @@ English | [简体中文](README_ZH.md)
 
 </div>
 
+#### Default configs do not enable custom CUDA kernel acceleration, but I strongly recommend that you enable it and run with int8 precision, which is much faster and consumes much less VRAM. Go to the Configs page and turn on `Use Custom CUDA kernel to Accelerate`.
+
 ## Features
 
 - RWKV model management and one-click startup
diff --git a/README_ZH.md b/README_ZH.md
index 51695f5..5f2ffe4 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -30,6 +30,8 @@ API兼容的接口，这意味着一切ChatGPT客户端都是RWKV客户端。
 
 #### 注意 目前RWKV中文模型质量一般，推荐使用英文模型体验实际RWKV能力
 
+#### 预设配置没有开启自定义CUDA算子加速，但我强烈建议你开启它并使用int8量化运行，速度非常快，且显存消耗少得多。前往配置页面，打开`使用自定义CUDA算子加速`
+
 ## 功能
 
 - RWKV模型管理，一键启动