fix(build): remove unnecessary GGML_BACKEND_DL flag for windows-gpu build

Author: Gioee

.github/workflows/main.yml

@@ -104,7 +104,7 @@ jobs:
           - os: windows-latest
             arch: x86_64
             name: windows-gpu
-            make: LLAMA="-G \"Ninja Multi-Config\" -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_CUDA=ON -DGGML_HIP=ON -DGGML_SYCL=ON"
+            make: LLAMA="-G \"Ninja Multi-Config\" -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_CUDA=ON -DGGML_HIP=ON -DGGML_SYCL=ON"
             make-cuda: LLAMA_ARGS="--target ggml-cuda" LLAMA="-G \"Ninja Multi-Config\" -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_CUDA=ON"
             make-hip: LLAMA_ARGS="--target ggml-hip" LLAMA="-G \"Ninja\" -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_HIP=ON -DGGML_HIP_ROCWMMA_FATTN=ON -DAMDGPU_TARGETS=\"gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032\" -DCMAKE_C_COMPILER=\"%HIP_PATH%/bin/clang.exe\" -DCMAKE_CXX_COMPILER=\"%HIP_PATH%/bin/clang++.exe\" -DCMAKE_CXX_FLAGS=\"-I../../rocwmma/library/include/ -Wno-ignored-attributes -Wno-nested-anon-types\""
             make-sycl: LLAMA_ARGS="--target ggml-sycl" LLAMA="-G \"Ninja\" -DGGML_BACKEND_DL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_SYCL=ON"