Merge branch 'main' into batched-box-ops

Author: scotts

.github/scripts/run-clang-format.py

@@ -18,7 +18,7 @@ jobs:
             gpu-arch-type: cpu
           - runner: linux.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:
@@ -66,7 +66,7 @@ jobs:
             gpu-arch-type: cpu
           - runner: windows.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/windows_job.yml@main
     with:

.github/workflows/build-cmake.yml

@@ -25,7 +25,7 @@ jobs:
       os: linux-aarch64
       test-infra-repository: pytorch/test-infra
       test-infra-ref: main
-      with-cuda: disable
+      with-cuda: enable
   build:
     needs: generate-matrix
     strategy: