@@ -504,13 +504,13 @@ You could download the release package for Windows directly, which including bin
504504
505505Choose one of following methods to build from source code.
506506
507- 1 . Script
507+ #### 1. Script
508508
509509``` sh
510510.\e xamples\s ycl\w in-build-sycl.bat
511511```
512512
513- 2 . CMake
513+ #### 2. CMake
514514
515515On the oneAPI command line window, step into the llama.cpp main directory and run the following:
516516
@@ -539,7 +539,7 @@ cmake --preset x64-windows-sycl-debug
539539cmake --build build-x64-windows-sycl-debug -j --target llama-cli
540540```
541541
542- 3 . Visual Studio
542+ #### 3. Visual Studio
543543
544544You have two options to use Visual Studio to build llama.cpp:
545545- As CMake Project using CMake presets.
@@ -549,7 +549,7 @@ You have two options to use Visual Studio to build llama.cpp:
549549
550550All following commands are executed in PowerShell.
551551
552- 1 . Open as a CMake Project
552+ ###### - Open as a CMake Project
553553
554554You can use Visual Studio to open the ` llama.cpp ` folder directly as a CMake project. Before compiling, select one of the SYCL CMake presets:
555555
@@ -564,7 +564,7 @@ You can use Visual Studio to open the `llama.cpp` folder directly as a CMake pro
564564 cmake --build build --config Release -j --target llama-cli
565565 ```
566566
567- 2. Generating a Visual Studio Solution
567+ ###### - Generating a Visual Studio Solution
568568
569569You can use Visual Studio solution to build and work on llama.cpp on Windows. You need to convert the CMake Project into a `.sln` file.
570570
@@ -589,8 +589,6 @@ cmake -B build -G "Visual Studio 17 2022" -A x64 -DGGML_SYCL=ON -DCMAKE_BUILD_TY
589589If successful the build files have been written to: * path/to/llama.cpp/build*
590590Open the project file ** build/llama.cpp.sln** with Visual Studio.
591591
592- - Configuring SYCL Offload in Visual Studio
593-
594592Once the Visual Studio solution is created, follow these steps:
595593
5965941 . Open the solution in Visual Studio.
@@ -610,8 +608,6 @@ Once the Visual Studio solution is created, follow these steps:
610608Properties -> C/C++ -> DPC++ -> Enable SYCL Offload (Yes)
611609```
612610
613- - Build
614-
615611Now, you can build ` llama.cpp ` with the SYCL backend as a Visual Studio project.
616612To do it from menu: ` Build -> Build Solution ` .
617613Once it is completed, final results will be in ** build/Release/bin**
0 commit comments