fix(windows): readd missing cutlass test

Author: mfuntowicz

.github/workflows/build_kernel_windows.yaml

@@ -60,10 +60,10 @@ jobs:
       - name: Install PyTorch
         run: pip install torch --index-url https://download.pytorch.org/whl/cu${{ matrix.torch.wheel }}
 
-#      - name: Build cutlass GEMM kernel
-#        run: ( scripts\windows\builder.ps1 -SourceFolder examples/cutlass-gemm -BuildConfig Release -Backend cuda -Build -Force )
-#      - name: Copy cutlass GEMM kernel
-#        run: cp -rL examples/cutlass-gemm/result cutlass-gemm-kernel
+      - name: Build cutlass GEMM kernel
+        run: ( scripts\windows\builder.ps1 -SourceFolder examples/cutlass-gemm -BuildConfig Release -Backend cuda -Build -Force )
+      - name: Copy cutlass GEMM kernel
+        run: cp -rL examples/cutlass-gemm/result cutlass-gemm-kernel
 
       - name: Build relu kernel
         run: ( scripts\windows\builder.ps1 -SourceFolder examples/relu -BuildConfig Release -Backend cuda -Build -Force )