Update CUDA version in workflow to 12.8

Author: larryliu0820

.github/workflows/cuda-windows.yml

@@ -15,9 +15,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
   cancel-in-progress: false
 
-env:
-  CUDA_VERSION: "12.8"
-
 jobs:
   export-model-cuda-windows-artifact:
     name: export-model-cuda-windows-artifact
@@ -44,7 +41,7 @@ jobs:
       secrets-env: EXECUTORCH_HF_TOKEN
       runner: linux.g5.4xlarge.nvidia.gpu
       gpu-arch-type: cuda
-      gpu-arch-version: ${{ env.CUDA_VERSION }}
+      gpu-arch-version: "12.8"
       docker-image: ci-image:executorch-ubuntu-22.04-cuda-windows
       submodules: recursive
       upload-artifact: ${{ matrix.model.repo }}-${{ matrix.model.name }}-cuda-windows-${{ matrix.quant }}
@@ -101,6 +98,8 @@ jobs:
           - "quantized-int4-weight-only"
     with:
       timeout: 240
+      gpu-arch-type: cuda
+      gpu-arch-version: "12.8"
       submodules: recursive
       download-artifact: ${{ matrix.model.repo }}-${{ matrix.model.name }}-cuda-windows-${{ matrix.quant }}
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -122,5 +121,5 @@ jobs:
             -HfModel '${{ matrix.model.repo }}/${{ matrix.model.name }}' `
             -QuantName '${{ matrix.quant }}' `
             -ModelDir \$artifactDir `
-            -ExpectedCudaVersion '${{ env.CUDA_VERSION }}'
+            -ExpectedCudaVersion '12.8'
         }"