From bc85865775e2db9b5a6ab7fadb1823c9a73a74cc Mon Sep 17 00:00:00 2001
From: PENG Bo <33809201+BlinkDL@users.noreply.github.com>
Date: Mon, 27 Jun 2022 12:49:42 +0800
Subject: [PATCH] Update README.md

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

diff --git a/README.md b/README.md
index b369909..00b5f3e 100644
--- a/README.md
+++ b/README.md
@@ -101,6 +101,10 @@ I need a better CUDA kernel to (1) pull off maxK so there's need to clamp k to 6
 
 Removing the maxK limitation will also make it easy to clean the state of a KV-V channel, by using a huge K.
 
+Namely, this is what I plan to do:
+
+![RWKV-v3-plan](RWKV-v3-plan.png)
+
 ========================================================================
 
 ### Explaining the code for RWKV v2+ GPT mode