fix(ci): pass CUDA unsupported compiler flag during detection (abetlen#2201)

Author: abetlen

.github/workflows/build-wheels-cuda.yaml

@@ -167,7 +167,7 @@ jobs:
           # Build real cubins for the supported GPUs, including sm_70, and keep
           # one forward-compatible PTX target instead of embedding PTX for every
           # SM. This keeps the wheel under GitHub's 2 GiB release-asset limit.
-          $env:CMAKE_ARGS = "-DGGML_CUDA_FORCE_MMQ=ON -DGGML_CUDA=on -DCMAKE_CUDA_ARCHITECTURES=70-real;75-real;80-real;86-real;89-real;90-real;90-virtual -DCMAKE_CUDA_FLAGS=--allow-unsupported-compiler $env:CMAKE_ARGS"
+          $env:CMAKE_ARGS = "-DGGML_CUDA_FORCE_MMQ=ON -DGGML_CUDA=on -DCMAKE_CUDA_ARCHITECTURES=70-real;75-real;80-real;86-real;89-real;90-real;90-virtual -DCMAKE_CUDA_FLAGS=--allow-unsupported-compiler -DCMAKE_CUDA_FLAGS_INIT=--allow-unsupported-compiler $env:CMAKE_ARGS"
           $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DGGML_AVX2=off -DGGML_FMA=off -DGGML_F16C=off'
           python -m build --wheel
           # Publish tags that reflect the actual installed toolkit version.