From 6627f7feb9afe106df89e0b290adde21b1f8c914 Mon Sep 17 00:00:00 2001
From: AlpinDale <52078762+AlpinDale@users.noreply.github.com>
Date: Wed, 31 May 2023 05:58:53 +0430
Subject: [PATCH] Add notice about downgrading `gcc` and `g++` (#2446)

---
 docs/GPTQ-models-(4-bit-mode).md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/GPTQ-models-(4-bit-mode).md b/docs/GPTQ-models-(4-bit-mode).md
index 3aa3cf8b..8b0a4f01 100644
--- a/docs/GPTQ-models-(4-bit-mode).md
+++ b/docs/GPTQ-models-(4-bit-mode).md
@@ -78,6 +78,7 @@ git clone https://github.com/oobabooga/GPTQ-for-LLaMa.git -b cuda
 cd GPTQ-for-LLaMa
 python setup_cuda.py install
 ```
+>If you're using an older version of CUDA toolkit (e.g. 11.7) but the latest version of `gcc` and `g++` (12.0+), you should downgrade with: `conda install -c conda-forge gxx==11.3.0`. Kernel compilation will fail otherwise.
 
 You are going to need to have a C++ compiler installed into your system for the last command. On Linux, `sudo apt install build-essential` or equivalent is enough.