diff --git a/.github/workflows/nightly_tests.yml b/.github/workflows/nightly_tests.yml
index 88343a128bb1..7696852ecd44 100644
--- a/.github/workflows/nightly_tests.yml
+++ b/.github/workflows/nightly_tests.yml
@@ -180,6 +180,55 @@ jobs:
         pip install slack_sdk tabulate
         python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
+  run_torch_compile_tests:
+    name: PyTorch Compile CUDA tests
+
+    runs-on:
+      group: aws-g4dn-2xlarge
+
+    container:
+      image: diffusers/diffusers-pytorch-compile-cuda
+      options: --gpus 0 --shm-size "16gb" --ipc host
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: NVIDIA-SMI
+      run: |
+        nvidia-smi
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
+    - name: Environment
+      run: |
+        python utils/print_env.py
+    - name: Run torch compile tests on GPU
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        RUN_COMPILE: yes
+      run: |
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_torch_compile_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: torch_compile_test_reports
+        path: reports
+
+    - name: Generate Report and Notify Channel
+      if: always()
+      run: |
+        pip install slack_sdk tabulate
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+  
   run_big_gpu_torch_tests:
     name: Torch tests on big GPU
     strategy:
diff --git a/.github/workflows/release_tests_fast.yml b/.github/workflows/release_tests_fast.yml
index 27bd9bd9bb42..9d65db2f0dee 100644
--- a/.github/workflows/release_tests_fast.yml
+++ b/.github/workflows/release_tests_fast.yml
@@ -335,7 +335,7 @@ jobs:
     - name: Environment
       run: |
         python utils/print_env.py
-    - name: Run example tests on GPU
+    - name: Run torch compile tests on GPU
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
diff --git a/tests/models/test_modeling_common.py b/tests/models/test_modeling_common.py
index f82a2407f333..a7a42368a84d 100644
--- a/tests/models/test_modeling_common.py
+++ b/tests/models/test_modeling_common.py
@@ -1714,6 +1714,37 @@ def test_push_to_hub_library_name(self):
         delete_repo(self.repo_id, token=TOKEN)
 
 
+class TorchCompileTesterMixin:
+    def setUp(self):
+        # clean up the VRAM before each test
+        super().setUp()
+        torch._dynamo.reset()
+        gc.collect()
+        backend_empty_cache(torch_device)
+
+    def tearDown(self):
+        # clean up the VRAM after each test in case of CUDA runtime errors
+        super().tearDown()
+        torch._dynamo.reset()
+        gc.collect()
+        backend_empty_cache(torch_device)
+
+    @require_torch_gpu
+    @require_torch_2
+    @is_torch_compile
+    @slow
+    def test_torch_compile_recompilation_and_graph_break(self):
+        torch._dynamo.reset()
+        init_dict, inputs_dict = self.prepare_init_args_and_inputs_for_common()
+
+        model = self.model_class(**init_dict).to(torch_device)
+        model = torch.compile(model, fullgraph=True)
+
+        with torch._dynamo.config.patch(error_on_recompile=True), torch.no_grad():
+            _ = model(**inputs_dict)
+            _ = model(**inputs_dict)
+
+
 @slow
 @require_torch_2
 @require_torch_accelerator
diff --git a/tests/models/transformers/test_models_transformer_flux.py b/tests/models/transformers/test_models_transformer_flux.py
index c88b3dac8216..f767d2196e7c 100644
--- a/tests/models/transformers/test_models_transformer_flux.py
+++ b/tests/models/transformers/test_models_transformer_flux.py
@@ -22,7 +22,7 @@
 from diffusers.models.embeddings import ImageProjection
 from diffusers.utils.testing_utils import enable_full_determinism, torch_device
 
-from ..test_modeling_common import ModelTesterMixin
+from ..test_modeling_common import ModelTesterMixin, TorchCompileTesterMixin
 
 
 enable_full_determinism()
@@ -78,7 +78,7 @@ def create_flux_ip_adapter_state_dict(model):
     return ip_state_dict
 
 
-class FluxTransformerTests(ModelTesterMixin, unittest.TestCase):
+class FluxTransformerTests(ModelTesterMixin, TorchCompileTesterMixin, unittest.TestCase):
     model_class = FluxTransformer2DModel
     main_input_name = "hidden_states"
     # We override the items here because the transformer under consideration is small.
diff --git a/tests/pipelines/test_pipelines_common.py b/tests/pipelines/test_pipelines_common.py
index a950de142740..eb420d1d2f12 100644
--- a/tests/pipelines/test_pipelines_common.py
+++ b/tests/pipelines/test_pipelines_common.py
@@ -1111,12 +1111,14 @@ def callback_cfg_params(self) -> frozenset:
     def setUp(self):
         # clean up the VRAM before each test
         super().setUp()
+        torch._dynamo.reset()
         gc.collect()
         backend_empty_cache(torch_device)
 
     def tearDown(self):
         # clean up the VRAM after each test in case of CUDA runtime errors
         super().tearDown()
+        torch._dynamo.reset()
         gc.collect()
         backend_empty_cache(torch_device)