diff --git a/README-sycl.md b/README-sycl.md index 2aa465070..a4f1b9d8e 100644 --- a/README-sycl.md +++ b/README-sycl.md @@ -229,12 +229,12 @@ source /opt/intel/oneapi/setvars.sh # Build LLAMA with MKL BLAS acceleration for intel GPU mkdir -p build && cd build -# Option 1: Use FP16 for better performance in long-prompt inference -#cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON - -# Option 2: Use FP32 by default +# Option 1: Use FP32 by default cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx +# Option 2: Use FP16 for better performance in long-prompt inference +cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON + #build all binary cmake --build . --config Release -j -v ``` @@ -250,12 +250,12 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR # Build LLAMA with Nvidia BLAS acceleration through SYCL mkdir -p build && cd build -# Option 1: Use FP16 for better performance in long-prompt inference -cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON - -# Option 2: Use FP32 by default +# Option 1: Use FP32 by default cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx +# Option 2: Use FP16 for better performance in long-prompt inference +cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON + #build all binary cmake --build . --config Release -j -v @@ -416,8 +416,13 @@ mkdir -p build cd build @call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force +# Option 1: Use FP32 by default +cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release + +# Option 2: Or FP16 cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON + make -j ```