Update README.md

README.md

@@ -585,7 +585,28 @@ Building the program with BLAS support may lead to some performance improvements
   | GGML_CUDA_KQUANTS_ITER | 1 or 2                 | 2       | Number of values processed per iteration and per HIP thread for Q2_K and Q6_K quantization formats. Setting this value to 1 can improve performance for slow GPUs.                                                                             |
 
 - #### Vulkan
-  ##### Windows (MSYS2)
+
+  **Windows**
+
+  ###### w64devkit
+
+  Download and extract [w64devkit](https://github.com/skeeto/w64devkit/releases).
+  
+  Download and install the [Vulkan SDK](https://vulkan.lunarg.com/sdk/home#windows).
+  
+  Create a `w64devkit/x86_64-w64-mingw32/lib/pkgconfig/vulkan.pc` file with the following contents:
+  
+  _Note: make sure the path matches the version in SDK download_.
+  ```
+  Name: Vulkan-Loader
+  Description: Vulkan Loader
+  Version: 1.3.283
+  Libs: -L/VulkanSDK/1.3.283.0/Lib -lvulkan-1
+  Cflags: -I/VulkanSDK/1.3.283.0/Include
+  ```
+  Launch `w64devkit.exe`, switch into `llama.cpp` directory and run `make GGML_VULKAN=1`.
+  
+  ###### MSYS2
   Install [MSYS2](https://www.msys2.org/) and then run the following commands in a UCRT terminal to install dependencies.
     ```sh
     pacman -S git \
@@ -596,7 +617,7 @@ Building the program with BLAS support may lead to some performance improvements
     ```
   Switch into `llama.cpp` directory and build using CMake.
   ```sh
-  cmake -B build -DLLAMA_VULKAN=ON
+  cmake -B build -DGGML_VULKAN=ON
   cmake --build build --config Release
   ```