From 8d198e01719c69e1910c76ad7f406707830ea45f Mon Sep 17 00:00:00 2001
From: John Smith <yfshi123@163.com>
Date: Tue, 21 Mar 2023 16:48:17 +0800
Subject: [PATCH] Update README.md

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

diff --git a/README.md b/README.md
index 7f2e90d..bf8eac8 100644
--- a/README.md
+++ b/README.md
@@ -3,6 +3,8 @@ Made some adjust for the code in peft and gptq for llama, and make it possible f
 <br>
 ~Still numerically unstable.~ Resolved.
 <br>
+Reconstruct fp16 matrix from 4bit data and call torch.matmul drastically increased the inference speed.
+<br>
 # Requirements
 gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa<br>
 peft: https://github.com/huggingface/peft.git<br>