diff --git a/.github/workflows/pull.yml b/.github/workflows/pull.yml
index cc2c4e89664..3fe8ac15a30 100644
--- a/.github/workflows/pull.yml
+++ b/.github/workflows/pull.yml
@@ -254,42 +254,6 @@ jobs:
       timeout-minutes: 600
     secrets: inherit
 
-  linux-jammy-cuda12_8-py3_10-gcc11-build:
-    name: linux-jammy-cuda12.8-py3.10-gcc11
-    uses: ./.github/workflows/_linux-build.yml
-    needs: get-label-type
-    with:
-      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
-      build-environment: linux-jammy-cuda12.8-py3.10-gcc11
-      docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3-gcc11
-      cuda-arch-list: '7.5 8.9'
-      test-matrix: |
-        { include: [
-          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
-          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
-          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
-          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
-          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
-          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
-          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
-          { config: "pr_time_benchmarks", shard: 1, num_shards: 1, runner: "linux.g4dn.metal.nvidia.gpu" },
-        ]}
-    secrets: inherit
-
-  linux-jammy-cuda12_8-py3_10-gcc11-test:
-    name: linux-jammy-cuda12.8-py3.10-gcc11
-    uses: ./.github/workflows/_linux-test.yml
-    needs:
-      - linux-jammy-cuda12_8-py3_10-gcc11-build
-      - target-determination
-    with:
-      timeout-minutes: 360
-      build-environment: linux-jammy-cuda12.8-py3.10-gcc11
-      docker-image: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.test-matrix }}
-    secrets: inherit
-
   linux-jammy-cuda12_8-cudnn9-py3_9-clang12-build:
     name: linux-jammy-cuda12.8-cudnn9-py3.9-clang12
     uses: ./.github/workflows/_linux-build.yml
diff --git a/.github/workflows/trunk.yml b/.github/workflows/trunk.yml
index c7cf4c84e18..19b0e88b592 100644
--- a/.github/workflows/trunk.yml
+++ b/.github/workflows/trunk.yml
@@ -63,6 +63,43 @@ jobs:
         ]}
     secrets: inherit
 
+  linux-jammy-cuda12_8-py3_10-gcc11-build:
+    name: linux-jammy-cuda12.8-py3.10-gcc11
+    uses: ./.github/workflows/_linux-build.yml
+    needs: get-label-type
+    with:
+      runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
+      build-environment: linux-jammy-cuda12.8-py3.10-gcc11
+      docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3-gcc11
+      cuda-arch-list: '7.5 8.9'
+      test-matrix: |
+        { include: [
+          { config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
+          { config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
+          { config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
+          { config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
+          { config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
+          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
+          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
+          { config: "pr_time_benchmarks", shard: 1, num_shards: 1, runner: "linux.g4dn.metal.nvidia.gpu" },
+        ]}
+    secrets: inherit
+
+  linux-jammy-cuda12_8-py3_10-gcc11-test:
+    name: linux-jammy-cuda12.8-py3.10-gcc11
+    uses: ./.github/workflows/_linux-test.yml
+    needs:
+      - linux-jammy-cuda12_8-py3_10-gcc11-build
+      - target-determination
+    with:
+      timeout-minutes: 360
+      build-environment: linux-jammy-cuda12.8-py3.10-gcc11
+      docker-image: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.test-matrix }}
+    secrets: inherit
+
+
   # no-ops builds test USE_PER_OPERATOR_HEADERS=0 where ATen/ops is not generated
   linux-jammy-cuda12_8-py3_10-gcc11-no-ops-build:
     name: linux-jammy-cuda12.8-py3.10-gcc11-no-ops