@@ -504,13 +504,13 @@ You could download the release package for Windows directly, which including bin
504
504
505
505
Choose one of following methods to build from source code.
506
506
507
- 1 . Script
507
+ #### 1. Script
508
508
509
509
``` sh
510
510
.\e xamples\s ycl\w in-build-sycl.bat
511
511
```
512
512
513
- 2 . CMake
513
+ #### 2. CMake
514
514
515
515
On the oneAPI command line window, step into the llama.cpp main directory and run the following:
516
516
@@ -539,7 +539,7 @@ cmake --preset x64-windows-sycl-debug
539
539
cmake --build build-x64-windows-sycl-debug -j --target llama-cli
540
540
```
541
541
542
- 3 . Visual Studio
542
+ #### 3. Visual Studio
543
543
544
544
You have two options to use Visual Studio to build llama.cpp:
545
545
- As CMake Project using CMake presets.
@@ -549,7 +549,7 @@ You have two options to use Visual Studio to build llama.cpp:
549
549
550
550
All following commands are executed in PowerShell.
551
551
552
- 1 . Open as a CMake Project
552
+ ###### - Open as a CMake Project
553
553
554
554
You can use Visual Studio to open the ` llama.cpp ` folder directly as a CMake project. Before compiling, select one of the SYCL CMake presets:
555
555
@@ -564,7 +564,7 @@ You can use Visual Studio to open the `llama.cpp` folder directly as a CMake pro
564
564
cmake --build build --config Release -j --target llama-cli
565
565
```
566
566
567
- 2. Generating a Visual Studio Solution
567
+ ###### - Generating a Visual Studio Solution
568
568
569
569
You 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.
570
570
@@ -589,8 +589,6 @@ cmake -B build -G "Visual Studio 17 2022" -A x64 -DGGML_SYCL=ON -DCMAKE_BUILD_TY
589
589
If successful the build files have been written to: * path/to/llama.cpp/build*
590
590
Open the project file ** build/llama.cpp.sln** with Visual Studio.
591
591
592
- - Configuring SYCL Offload in Visual Studio
593
-
594
592
Once the Visual Studio solution is created, follow these steps:
595
593
596
594
1 . Open the solution in Visual Studio.
@@ -610,8 +608,6 @@ Once the Visual Studio solution is created, follow these steps:
610
608
Properties -> C/C++ -> DPC++ -> Enable SYCL Offload (Yes)
611
609
```
612
610
613
- - Build
614
-
615
611
Now, you can build ` llama.cpp ` with the SYCL backend as a Visual Studio project.
616
612
To do it from menu: ` Build -> Build Solution ` .
617
613
Once it is completed, final results will be in ** build/Release/bin**
0 commit comments