From cd9be4c2ba4de3c46e475747d51b207f489591f6 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 16 May 2023 00:49:32 -0300
Subject: [PATCH] Update llama.cpp-models.md

---
 docs/llama.cpp-models.md | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/docs/llama.cpp-models.md b/docs/llama.cpp-models.md
index 4ed00dca..153f70af 100644
--- a/docs/llama.cpp-models.md
+++ b/docs/llama.cpp-models.md
@@ -16,11 +16,22 @@ Enabled with the `--n-gpu-layers` parameter. If you have enough VRAM, use a high
 
 Note that you need to manually install `llama-cpp-python` with GPU support. To do that:
 
+#### Linux
+
 ```
 pip uninstall -y llama-cpp-python
 CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir
 ```
 
+#### Windows
+
+```
+pip uninstall -y llama-cpp-python
+set CMAKE_ARGS="-DLLAMA_CUBLAS=on"
+set FORCE_CMAKE=1
+pip install llama-cpp-python --no-cache-dir
+```
+
 Here you can find the different compilation options for OpenBLAS / cuBLAS / CLBlast: https://pypi.org/project/llama-cpp-python/
 
 ## Performance