From 02089baf7039c088291137fd2bf65efeb7dfe855 Mon Sep 17 00:00:00 2001
From: Jeffrey Morgan <jmorganca@gmail.com>
Date: Sat, 18 May 2024 19:49:43 -0700
Subject: [PATCH] Update README.md

---
 llama/README.md | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/llama/README.md b/llama/README.md
index a3bb509e..cd2ce81a 100644
--- a/llama/README.md
+++ b/llama/README.md
@@ -44,12 +44,13 @@ go build -tags=avx2 .
 
 Install the [CUDA toolkit v11.3.1](https://developer.nvidia.com/cuda-11-3-1-download-archive) then build ggml-cuda:
 
+Build `ggml-cuda.dll`:
+
 ```shell
-# builds ggml-cuda.dll
 ./cuda.sh
 ```
 
-Then build this package with the `cuda` tag:
+Then build the package with the `cuda` tag:
 
 ```shell
 go build -tags=cuda .
@@ -57,17 +58,24 @@ go build -tags=cuda .
 
 ### ROCm
 
+Install [ROCm 5.7.1](https://rocm.docs.amd.com/en/docs-5.7.1/) and [Strawberry Perl](https://strawberryperl.com/):
+
+Build `ggml-hipblas.dll`:
+
 ```shell
-# builds ggml-hipblas.dll
 ./hipblas.sh
 ```
 
+Then build the package with the `rocm` tag:
+
 ```shell
 go build -tags=rocm .
 ```
 
 ## Syncing with llama.cpp
 
+To update this package to the latest llama.cpp code, use the `sync.sh` script.
+
 ```
 ./sync.sh ../../llama.cpp
 ```