diff --git a/.github/workflows/cron.yml b/.github/workflows/cron.yml
index e13848f8fc..2e7921ec94 100644
--- a/.github/workflows/cron.yml
+++ b/.github/workflows/cron.yml
@@ -13,16 +13,12 @@ jobs:
     strategy:
       matrix:
         environment:
-          - "PT110+CUDA113"
           - "PT113+CUDA118"
           - "PT210+CUDA121"
           - "PT240+CUDA126"
           - "PTLATEST+CUDA126"
         include:
           # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes
-          - environment: PT110+CUDA113
-            pytorch: "torch==1.10.2 torchvision==0.11.3 --extra-index-url https://download.pytorch.org/whl/cu113"
-            base: "nvcr.io/nvidia/pytorch:21.06-py3"  # CUDA 11.3
           - environment: PT113+CUDA118
             pytorch: "torch==1.13.1 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu121"
             base: "nvcr.io/nvidia/pytorch:22.10-py3"  # CUDA 11.8
diff --git a/.github/workflows/pythonapp-gpu.yml b/.github/workflows/pythonapp-gpu.yml
index d8623c8087..cd916f2ebb 100644
--- a/.github/workflows/pythonapp-gpu.yml
+++ b/.github/workflows/pythonapp-gpu.yml
@@ -22,20 +22,10 @@ jobs:
     strategy:
       matrix:
         environment:
-          - "PT19+CUDA114DOCKER"
-          - "PT110+CUDA111"
-          - "PT112+CUDA118DOCKER"
           - "PT113+CUDA116"
           - "PT210+CUDA121DOCKER"
         include:
           # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes
-          - environment: PT110+CUDA111
-            pytorch: "torch==1.10.2 torchvision==0.11.3 --extra-index-url https://download.pytorch.org/whl/cu111"
-            base: "nvcr.io/nvidia/cuda:11.1.1-devel-ubuntu18.04"
-          - environment: PT112+CUDA118DOCKER
-            # 22.09: 1.13.0a0+d0d6b1f
-            pytorch: "-h"  # we explicitly set pytorch to -h to avoid pip install error
-            base: "nvcr.io/nvidia/pytorch:22.09-py3"
           - environment: PT113+CUDA116
             pytorch: "torch==1.13.1 torchvision==0.14.1"
             base: "nvcr.io/nvidia/cuda:11.6.1-devel-ubuntu18.04"
@@ -59,8 +49,7 @@ jobs:
         apt-get update
         apt-get install -y wget
 
-        if [ ${{ matrix.environment }} = "PT110+CUDA111" ] || \
-          [ ${{ matrix.environment }} = "PT113+CUDA116" ]
+        if [ ${{ matrix.environment }} = "PT113+CUDA116" ]
         then
         PYVER=3.9 PYSFX=3 DISTUTILS=python3-distutils && \
         apt-get update && apt-get install -y --no-install-recommends \
@@ -94,9 +83,6 @@ jobs:
         python get-pip.py && \
         rm get-pip.py;
         fi
-    - if: matrix.environment == 'PT19+CUDA114DOCKER'
-      name: Optional Cupy dependency (cuda114)
-      run: echo "cupy-cuda114" >> requirements-dev.txt
     - name: Install dependencies
       if: github.event.pull_request.merged != true
       run: |
diff --git a/.github/workflows/pythonapp-min.yml b/.github/workflows/pythonapp-min.yml
index b0d37937e9..c94a94ed89 100644
--- a/.github/workflows/pythonapp-min.yml
+++ b/.github/workflows/pythonapp-min.yml
@@ -124,7 +124,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        pytorch-version: ['1.10.2', '1.11.0', '1.12.1', '1.13', '2.0.1', 'latest']
+        pytorch-version: ['1.13.1', '2.0.1', 'latest']
     timeout-minutes: 40
     steps:
     - uses: actions/checkout@v4
diff --git a/.github/workflows/pythonapp.yml b/.github/workflows/pythonapp.yml
index 3c39166c1e..f175cc3f7c 100644
--- a/.github/workflows/pythonapp.yml
+++ b/.github/workflows/pythonapp.yml
@@ -155,7 +155,7 @@ jobs:
         # install the latest pytorch for testing
         # however, "pip install monai*.tar.gz" will build cpp/cuda with an isolated
         # fresh torch installation according to pyproject.toml
-        python -m pip install torch>=1.9 torchvision
+        python -m pip install torch>=1.13.1 torchvision
     - name: Check packages
       run: |
         pip uninstall monai
diff --git a/docs/requirements.txt b/docs/requirements.txt
index 7307d8e5f9..d657580743 100644
--- a/docs/requirements.txt
+++ b/docs/requirements.txt
@@ -1,5 +1,5 @@
--f https://download.pytorch.org/whl/cpu/torch-1.12.1%2Bcpu-cp37-cp37m-linux_x86_64.whl
-torch>=1.9
+-f https://download.pytorch.org/whl/cpu/torch-1.13.1%2Bcpu-cp39-cp39-linux_x86_64.whl
+torch>=1.13.1
 pytorch-ignite==0.4.11
 numpy>=1.20
 itk>=5.2
diff --git a/environment-dev.yml b/environment-dev.yml
index 4a1723e8a5..8617a3b9cb 100644
--- a/environment-dev.yml
+++ b/environment-dev.yml
@@ -6,7 +6,7 @@ channels:
   - conda-forge
 dependencies:
   - numpy>=1.24,<2.0
-  - pytorch>=1.9
+  - pytorch>=1.13.1
   - torchio
   - torchvision
   - pytorch-cuda>=11.6
diff --git a/monai/apps/auto3dseg/transforms.py b/monai/apps/auto3dseg/transforms.py
index bb755aa78c..28f82e3725 100644
--- a/monai/apps/auto3dseg/transforms.py
+++ b/monai/apps/auto3dseg/transforms.py
@@ -18,7 +18,6 @@
 import torch
 
 from monai.config import KeysCollection
-from monai.networks.utils import pytorch_after
 from monai.transforms import MapTransform
 from monai.utils.misc import ImageMetaKey
 
@@ -76,7 +75,7 @@ def __call__(self, data: Mapping[Hashable, torch.Tensor]) -> dict[Hashable, torc
                     d[key] = torch.nn.functional.interpolate(
                         input=d[key].unsqueeze(0),
                         size=image_shape,
-                        mode="nearest-exact" if pytorch_after(1, 11) else "nearest",
+                        mode="nearest-exact",
                     ).squeeze(0)
                 else:
                     raise ValueError(
diff --git a/monai/data/utils.py b/monai/data/utils.py
index f35c5124d8..d03dbd3234 100644
--- a/monai/data/utils.py
+++ b/monai/data/utils.py
@@ -50,7 +50,6 @@
     issequenceiterable,
     look_up_option,
     optional_import,
-    pytorch_after,
 )
 
 pd, _ = optional_import("pandas")
@@ -450,12 +449,9 @@ def collate_meta_tensor_fn(batch, *, collate_fn_map=None):
     Collate a sequence of meta tensor into a single batched metatensor. This is called by `collage_meta_tensor`
     and so should not be used as a collate function directly in dataloaders.
     """
-    if pytorch_after(1, 13):
-        from torch.utils.data._utils.collate import collate_tensor_fn  # imported here for pylint/mypy issues
+    from torch.utils.data._utils.collate import collate_tensor_fn  # imported here for pylint/mypy issues
 
-        collated = collate_tensor_fn(batch)
-    else:
-        collated = default_collate(batch)
+    collated = collate_tensor_fn(batch)
 
     meta_dicts = [i.meta or TraceKeys.NONE for i in batch]
     common_ = set.intersection(*[set(d.keys()) for d in meta_dicts if isinstance(d, dict)])
@@ -494,18 +490,15 @@ def list_data_collate(batch: Sequence):
         Need to use this collate if apply some transforms that can generate batch data.
 
     """
+    from torch.utils.data._utils.collate import default_collate_fn_map
 
-    if pytorch_after(1, 13):
-        # needs to go here to avoid circular import
-        from torch.utils.data._utils.collate import default_collate_fn_map
-
-        from monai.data.meta_tensor import MetaTensor
+    from monai.data.meta_tensor import MetaTensor
 
-        default_collate_fn_map.update({MetaTensor: collate_meta_tensor_fn})
+    default_collate_fn_map.update({MetaTensor: collate_meta_tensor_fn})
     elem = batch[0]
     data = [i for k in batch for i in k] if isinstance(elem, list) else batch
     key = None
-    collate_fn = default_collate if pytorch_after(1, 13) else collate_meta_tensor
+    collate_fn = default_collate
     try:
         if config.USE_META_DICT:
             data = pickle_operations(data)  # bc 0.9.0
diff --git a/monai/inferers/utils.py b/monai/inferers/utils.py
index edaf736091..8adba8fa25 100644
--- a/monai/inferers/utils.py
+++ b/monai/inferers/utils.py
@@ -31,11 +31,10 @@
     fall_back_tuple,
     look_up_option,
     optional_import,
-    pytorch_after,
 )
 
 tqdm, _ = optional_import("tqdm", name="tqdm")
-_nearest_mode = "nearest-exact" if pytorch_after(1, 11) else "nearest"
+_nearest_mode = "nearest-exact"
 
 __all__ = ["sliding_window_inference"]
 
diff --git a/monai/losses/dice.py b/monai/losses/dice.py
index 4108820bec..ee45b5c3b2 100644
--- a/monai/losses/dice.py
+++ b/monai/losses/dice.py
@@ -25,7 +25,7 @@
 from monai.losses.spatial_mask import MaskedLoss
 from monai.losses.utils import compute_tp_fp_fn
 from monai.networks import one_hot
-from monai.utils import DiceCEReduction, LossReduction, Weight, look_up_option, pytorch_after
+from monai.utils import DiceCEReduction, LossReduction, Weight, look_up_option
 
 
 class DiceLoss(_Loss):
@@ -738,12 +738,9 @@ def __init__(
             batch=batch,
             weight=dice_weight,
         )
-        if pytorch_after(1, 10):
-            self.cross_entropy = nn.CrossEntropyLoss(
-                weight=weight, reduction=reduction, label_smoothing=label_smoothing
-            )
-        else:
-            self.cross_entropy = nn.CrossEntropyLoss(weight=weight, reduction=reduction)
+        self.cross_entropy = nn.CrossEntropyLoss(
+            weight=weight, reduction=reduction, label_smoothing=label_smoothing
+        )
         self.binary_cross_entropy = nn.BCEWithLogitsLoss(pos_weight=weight, reduction=reduction)
         if lambda_dice < 0.0:
             raise ValueError("lambda_dice should be no less than 0.0.")
@@ -751,7 +748,6 @@ def __init__(
             raise ValueError("lambda_ce should be no less than 0.0.")
         self.lambda_dice = lambda_dice
         self.lambda_ce = lambda_ce
-        self.old_pt_ver = not pytorch_after(1, 10)
 
     def ce(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:
         """
@@ -764,12 +760,6 @@ def ce(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:
         if n_pred_ch != n_target_ch and n_target_ch == 1:
             target = torch.squeeze(target, dim=1)
             target = target.long()
-        elif self.old_pt_ver:
-            warnings.warn(
-                f"Multichannel targets are not supported in this older Pytorch version {torch.__version__}. "
-                "Using argmax (as a workaround) to convert target to a single channel."
-            )
-            target = torch.argmax(target, dim=1)
         elif not torch.is_floating_point(target):
             target = target.to(dtype=input.dtype)
 
diff --git a/monai/losses/ds_loss.py b/monai/losses/ds_loss.py
index aacc16874d..6a604aa22d 100644
--- a/monai/losses/ds_loss.py
+++ b/monai/losses/ds_loss.py
@@ -17,8 +17,6 @@
 import torch.nn.functional as F
 from torch.nn.modules.loss import _Loss
 
-from monai.utils import pytorch_after
-
 
 class DeepSupervisionLoss(_Loss):
     """
@@ -42,7 +40,7 @@ def __init__(self, loss: _Loss, weight_mode: str = "exp", weights: list[float] |
         self.loss = loss
         self.weight_mode = weight_mode
         self.weights = weights
-        self.interp_mode = "nearest-exact" if pytorch_after(1, 11) else "nearest"
+        self.interp_mode = "nearest-exact"
 
     def get_weights(self, levels: int = 1) -> list[float]:
         """
diff --git a/monai/networks/layers/simplelayers.py b/monai/networks/layers/simplelayers.py
index 4acd4a3622..6d34c3fa77 100644
--- a/monai/networks/layers/simplelayers.py
+++ b/monai/networks/layers/simplelayers.py
@@ -31,7 +31,6 @@
     issequenceiterable,
     look_up_option,
     optional_import,
-    pytorch_after,
 )
 
 _C, _ = optional_import("monai._C")
@@ -293,14 +292,7 @@ def apply_filter(x: torch.Tensor, kernel: torch.Tensor, **kwargs) -> torch.Tenso
     x = x.view(1, kernel.shape[0], *spatials)
     conv = [F.conv1d, F.conv2d, F.conv3d][n_spatial - 1]
     if "padding" not in kwargs:
-        if pytorch_after(1, 10):
-            kwargs["padding"] = "same"
-        else:
-            # even-sized kernels are not supported
-            kwargs["padding"] = [(k - 1) // 2 for k in kernel.shape[2:]]
-    elif kwargs["padding"] == "same" and not pytorch_after(1, 10):
-        # even-sized kernels are not supported
-        kwargs["padding"] = [(k - 1) // 2 for k in kernel.shape[2:]]
+        kwargs["padding"] = "same"
 
     if "stride" not in kwargs:
         kwargs["stride"] = 1
@@ -372,11 +364,7 @@ def _make_coeffs(window_length, order):
         a = idx ** torch.arange(order + 1, dtype=torch.float, device="cpu").reshape(-1, 1)
         y = torch.zeros(order + 1, dtype=torch.float, device="cpu")
         y[0] = 1.0
-        return (
-            torch.lstsq(y, a).solution.squeeze()  # type: ignore
-            if not pytorch_after(1, 11)
-            else torch.linalg.lstsq(a, y).solution.squeeze()
-        )
+        return torch.linalg.lstsq(a, y).solution.squeeze()
 
 
 class HilbertTransform(nn.Module):
diff --git a/monai/networks/utils.py b/monai/networks/utils.py
index 1b4cb220ae..2279bed0b4 100644
--- a/monai/networks/utils.py
+++ b/monai/networks/utils.py
@@ -31,7 +31,7 @@
 from monai.apps.utils import get_logger
 from monai.config import PathLike
 from monai.utils.misc import ensure_tuple, save_obj, set_determinism
-from monai.utils.module import look_up_option, optional_import, pytorch_after
+from monai.utils.module import look_up_option, optional_import
 from monai.utils.type_conversion import convert_to_dst_type, convert_to_tensor
 
 onnx, _ = optional_import("onnx")
@@ -676,15 +676,6 @@ def convert_to_onnx(
                 torch_versioned_kwargs["verify"] = verify
                 verify = False
         else:
-            if not pytorch_after(1, 10):
-                if "example_outputs" not in kwargs:
-                    # https://github.com/pytorch/pytorch/blob/release/1.9/torch/onnx/__init__.py#L182
-                    raise TypeError(
-                        "example_outputs is required in scripting mode before PyTorch 1.10."
-                        "Please provide example outputs or use trace mode to export onnx model."
-                    )
-                torch_versioned_kwargs["example_outputs"] = kwargs["example_outputs"]
-                del kwargs["example_outputs"]
             mode_to_export = torch.jit.script(model, **kwargs)
 
         if torch.is_tensor(inputs) or isinstance(inputs, dict):
@@ -746,8 +737,7 @@ def convert_to_onnx(
         # compare onnx/ort and PyTorch results
         for r1, r2 in zip(torch_out, onnx_out):
             if isinstance(r1, torch.Tensor):
-                assert_fn = torch.testing.assert_close if pytorch_after(1, 11) else torch.testing.assert_allclose
-                assert_fn(r1.cpu(), convert_to_tensor(r2, dtype=r1.dtype), rtol=rtol, atol=atol)  # type: ignore
+                torch.testing.assert_close(r1.cpu(), convert_to_tensor(r2, dtype=r1.dtype), rtol=rtol, atol=atol)  # type: ignore
 
     return onnx_model
 
@@ -817,8 +807,7 @@ def convert_to_torchscript(
         # compare TorchScript and PyTorch results
         for r1, r2 in zip(torch_out, torchscript_out):
             if isinstance(r1, torch.Tensor) or isinstance(r2, torch.Tensor):
-                assert_fn = torch.testing.assert_close if pytorch_after(1, 11) else torch.testing.assert_allclose
-                assert_fn(r1, r2, rtol=rtol, atol=atol)  # type: ignore
+                torch.testing.assert_close(r1, r2, rtol=rtol, atol=atol)  # type: ignore
 
     return script_module
 
@@ -1031,8 +1020,7 @@ def convert_to_trt(
         # compare TorchScript and PyTorch results
         for r1, r2 in zip(torch_out, trt_out):
             if isinstance(r1, torch.Tensor) or isinstance(r2, torch.Tensor):
-                assert_fn = torch.testing.assert_close if pytorch_after(1, 11) else torch.testing.assert_allclose
-                assert_fn(r1, r2, rtol=rtol, atol=atol)  # type: ignore
+                torch.testing.assert_close(r1, r2, rtol=rtol, atol=atol)  # type: ignore
 
     return trt_model
 
diff --git a/monai/transforms/croppad/array.py b/monai/transforms/croppad/array.py
index 813f8c1d44..d5ca876e98 100644
--- a/monai/transforms/croppad/array.py
+++ b/monai/transforms/croppad/array.py
@@ -56,7 +56,6 @@
     ensure_tuple_rep,
     fall_back_tuple,
     look_up_option,
-    pytorch_after,
 )
 
 __all__ = [
@@ -392,11 +391,7 @@ def compute_slices(
                 roi_center_t = convert_to_tensor(data=roi_center, dtype=torch.int16, wrap_sequence=True, device="cpu")
                 roi_size_t = convert_to_tensor(data=roi_size, dtype=torch.int16, wrap_sequence=True, device="cpu")
                 _zeros = torch.zeros_like(roi_center_t)
-                half = (
-                    torch.divide(roi_size_t, 2, rounding_mode="floor")
-                    if pytorch_after(1, 8)
-                    else torch.floor_divide(roi_size_t, 2)
-                )
+                half = torch.divide(roi_size_t, 2, rounding_mode="floor")
                 roi_start_t = torch.maximum(roi_center_t - half, _zeros)
                 roi_end_t = torch.maximum(roi_start_t + roi_size_t, roi_start_t)
             else:
diff --git a/monai/transforms/utils.py b/monai/transforms/utils.py
index e7e1616e13..1ff0abc27c 100644
--- a/monai/transforms/utils.py
+++ b/monai/transforms/utils.py
@@ -68,7 +68,6 @@
     look_up_option,
     min_version,
     optional_import,
-    pytorch_after,
     unsqueeze_left,
     unsqueeze_right,
 )
@@ -2255,7 +2254,7 @@ def _to_torch_resample_interp_mode(interp_mode):
     if ret is not None:
         return ret
     _mapping = {
-        SplineMode.ZERO: InterpolateMode.NEAREST_EXACT if pytorch_after(1, 11) else InterpolateMode.NEAREST,
+        SplineMode.ZERO: InterpolateMode.NEAREST_EXACT,
         SplineMode.ONE: InterpolateMode.LINEAR,
         SplineMode.THREE: InterpolateMode.BICUBIC,
     }
diff --git a/monai/utils/tf32.py b/monai/utils/tf32.py
index cfb023bdeb..81f56477bb 100644
--- a/monai/utils/tf32.py
+++ b/monai/utils/tf32.py
@@ -60,16 +60,6 @@ def detect_default_tf32() -> bool:
         if not has_ampere_or_later():
             return False
 
-        from monai.utils.module import pytorch_after
-
-        if pytorch_after(1, 7, 0) and not pytorch_after(1, 12, 0):
-            warnings.warn(
-                "torch.backends.cuda.matmul.allow_tf32 = True by default.\n"
-                "  This value defaults to True when PyTorch version in [1.7, 1.11] and may affect precision.\n"
-                "  See https://docs.monai.io/en/latest/precision_accelerating.html#precision-and-accelerating"
-            )
-            may_enable_tf32 = True
-
         override_tf32_env_vars = {"NVIDIA_TF32_OVERRIDE": "1"}  # TORCH_ALLOW_TF32_CUBLAS_OVERRIDE not checked #6907
         for name, override_val in override_tf32_env_vars.items():
             if os.environ.get(name) == override_val:
diff --git a/monai/visualize/class_activation_maps.py b/monai/visualize/class_activation_maps.py
index 489a563818..39f26d0fbd 100644
--- a/monai/visualize/class_activation_maps.py
+++ b/monai/visualize/class_activation_maps.py
@@ -22,7 +22,7 @@
 
 from monai.config import NdarrayTensor
 from monai.transforms import ScaleIntensity
-from monai.utils import ensure_tuple, pytorch_after
+from monai.utils import ensure_tuple
 from monai.visualize.visualizer import default_upsampler
 
 __all__ = ["CAM", "GradCAM", "GradCAMpp", "ModelWithHooks", "default_normalizer"]
@@ -83,13 +83,10 @@ def __init__(
                 continue
             _registered.append(name)
             if self.register_backward:
-                if pytorch_after(1, 8):
-                    if "inplace" in mod.__dict__ and mod.__dict__["inplace"]:
-                        # inplace=True causes errors for register_full_backward_hook
-                        mod.__dict__["inplace"] = False
-                    mod.register_full_backward_hook(self.backward_hook(name))
-                else:
-                    mod.register_backward_hook(self.backward_hook(name))
+                if "inplace" in mod.__dict__ and mod.__dict__["inplace"]:
+                    # inplace=True causes errors for register_full_backward_hook
+                    mod.__dict__["inplace"] = False
+                mod.register_full_backward_hook(self.backward_hook(name))
             if self.register_forward:
                 mod.register_forward_hook(self.forward_hook(name))
         if self.target_layers and (len(_registered) != len(self.target_layers)):
diff --git a/pyproject.toml b/pyproject.toml
index 9dc9cf619b..8ad55b1c2c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -2,7 +2,7 @@
 requires = [
   "wheel",
   "setuptools",
-  "torch>=1.9",
+  "torch>=1.13.1",
   "ninja",
   "packaging"
 ]
diff --git a/requirements.txt b/requirements.txt
index e184322c13..46ff887c59 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,2 @@
-torch>=1.9
+torch>=1.13.1
 numpy>=1.24,<2.0
diff --git a/setup.cfg b/setup.cfg
index 0c69051218..66d9e19609 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -42,7 +42,7 @@ setup_requires =
     ninja
     packaging
 install_requires =
-    torch>=1.9
+    torch>=1.13.1
     numpy>=1.24,<2.0
 
 [options.extras_require]
diff --git a/tests/test_cachedataset.py b/tests/test_cachedataset.py
index dbb1b8f8f1..0c0a7ef286 100644
--- a/tests/test_cachedataset.py
+++ b/tests/test_cachedataset.py
@@ -22,7 +22,6 @@
 
 from monai.data import CacheDataset, DataLoader, PersistentDataset, SmartCacheDataset
 from monai.transforms import Compose, Lambda, LoadImaged, RandLambda, ThreadUnsafe, Transform
-from monai.utils.module import pytorch_after
 
 TEST_CASE_1 = [Compose([LoadImaged(keys=["image", "label", "extra"])]), (128, 128, 128)]
 
@@ -130,7 +129,7 @@ class TestCacheThread(unittest.TestCase):
     @parameterized.expand(TEST_DS)
     def test_thread_safe(self, persistent_workers, cache_workers, loader_workers):
         expected = [102, 202, 302, 402, 502, 602, 702, 802, 902, 1002]
-        _kwg = {"persistent_workers": persistent_workers} if pytorch_after(1, 8) else {}
+        _kwg = {"persistent_workers": persistent_workers}
         data_list = list(range(1, 11))
         dataset = CacheDataset(
             data=data_list, transform=_StatefulTransform(), cache_rate=1.0, num_workers=cache_workers, progress=False
diff --git a/tests/test_convert_to_onnx.py b/tests/test_convert_to_onnx.py
index 798c510800..e08737926b 100644
--- a/tests/test_convert_to_onnx.py
+++ b/tests/test_convert_to_onnx.py
@@ -20,7 +20,6 @@
 
 from monai.networks import convert_to_onnx
 from monai.networks.nets import SegResNet, UNet
-from monai.utils.module import pytorch_after
 from tests.utils import SkipIfBeforePyTorchVersion, SkipIfNoModule, optional_import, skip_if_quick
 
 if torch.cuda.is_available():
@@ -53,7 +52,7 @@ def test_unet(self, device, use_trace, use_ort):
         model = UNet(
             spatial_dims=2, in_channels=1, out_channels=3, channels=(16, 32, 64), strides=(2, 2), num_res_units=0
         )
-        if pytorch_after(1, 10) or use_trace:
+        if use_trace:
             onnx_model = convert_to_onnx(
                 model=model,
                 inputs=[torch.randn((16, 1, 32, 32), requires_grad=False)],
@@ -66,22 +65,6 @@ def test_unet(self, device, use_trace, use_ort):
                 rtol=rtol,
                 atol=atol,
             )
-        else:
-            # https://github.com/pytorch/pytorch/blob/release/1.9/torch/onnx/__init__.py#L182
-            # example_outputs is required in scripting mode before PyTorch 3.10
-            onnx_model = convert_to_onnx(
-                model=model,
-                inputs=[torch.randn((16, 1, 32, 32), requires_grad=False)],
-                input_names=["x"],
-                output_names=["y"],
-                example_outputs=[torch.randn((16, 3, 32, 32), requires_grad=False)],
-                verify=True,
-                device=device,
-                use_ort=use_ort,
-                use_trace=use_trace,
-                rtol=rtol,
-                atol=atol,
-            )
         self.assertTrue(isinstance(onnx_model, onnx.ModelProto))
 
     @parameterized.expand(TESTS_ORT)
diff --git a/tests/test_integration_sliding_window.py b/tests/test_integration_sliding_window.py
index 8b53e94941..2a1d52ebbc 100644
--- a/tests/test_integration_sliding_window.py
+++ b/tests/test_integration_sliding_window.py
@@ -26,7 +26,7 @@
 from monai.networks import eval_mode, predict_segmentation
 from monai.networks.nets import UNet
 from monai.transforms import EnsureChannelFirst, SaveImage
-from monai.utils import pytorch_after, set_determinism
+from monai.utils import set_determinism
 from tests.utils import DistTestCase, TimedCall, make_nifti_image, skip_if_quick
 
 
@@ -55,11 +55,8 @@ def _sliding_window_processor(_engine, batch):
             return predict_segmentation(seg_probs)
 
     def save_func(engine):
-        if pytorch_after(1, 9, 1):
-            for m in engine.state.output:
-                saver(m)
-        else:
-            saver(engine.state.output[0])
+        for m in engine.state.output:
+            saver(m)
 
     infer_engine = Engine(_sliding_window_processor)
     infer_engine.add_event_handler(Events.ITERATION_COMPLETED, save_func)
diff --git a/tests/test_integration_workflows.py b/tests/test_integration_workflows.py
index fafb66f675..a166790ece 100644
--- a/tests/test_integration_workflows.py
+++ b/tests/test_integration_workflows.py
@@ -54,7 +54,7 @@
 )
 from monai.utils import optional_import, set_determinism
 from tests.testing_data.integration_answers import test_integration_value
-from tests.utils import DistTestCase, TimedCall, assert_allclose, pytorch_after, skip_if_quick
+from tests.utils import DistTestCase, TimedCall, assert_allclose, skip_if_quick
 
 SummaryWriter, _ = optional_import("torch.utils.tensorboard", name="SummaryWriter")
 
@@ -149,7 +149,7 @@ def _forward_completed(self, engine):
         val_handlers=val_handlers,
         amp=bool(amp),
         to_kwargs={"memory_format": torch.preserve_format},
-        amp_kwargs={"dtype": torch.float16 if bool(amp) else torch.float32} if pytorch_after(1, 10, 0) else {},
+        amp_kwargs={"dtype": torch.float16 if bool(amp) else torch.float32},
     )
 
     train_postprocessing = Compose(
@@ -205,7 +205,7 @@ def _model_completed(self, engine):
         amp=bool(amp),
         optim_set_to_none=True,
         to_kwargs={"memory_format": torch.preserve_format},
-        amp_kwargs={"dtype": torch.float16 if bool(amp) else torch.float32} if pytorch_after(1, 10, 0) else {},
+        amp_kwargs={"dtype": torch.float16 if bool(amp) else torch.float32},
     )
     trainer.run()
 
diff --git a/tests/test_meta_tensor.py b/tests/test_meta_tensor.py
index 60b6019703..ebeb7c1199 100644
--- a/tests/test_meta_tensor.py
+++ b/tests/test_meta_tensor.py
@@ -17,7 +17,6 @@
 import string
 import tempfile
 import unittest
-import warnings
 from copy import deepcopy
 from multiprocessing.reduction import ForkingPickler
 
@@ -33,7 +32,6 @@
 from monai.data.utils import decollate_batch, list_data_collate
 from monai.transforms import BorderPadd, Compose, DivisiblePadd, FromMetaTensord, ToMetaTensord
 from monai.utils.enums import PostFix
-from monai.utils.module import pytorch_after
 from tests.utils import TEST_DEVICES, SkipIfBeforePyTorchVersion, assert_allclose, skip_if_no_cuda
 
 DTYPES = [[torch.float32], [torch.float64], [torch.float16], [torch.int64], [torch.int32], [None]]
@@ -241,14 +239,6 @@ def test_torchscript(self, device):
             traced_fn = torch.jit.load(fname)
             out = traced_fn(im)
             self.assertIsInstance(out, torch.Tensor)
-            if not isinstance(out, MetaTensor) and not pytorch_after(1, 9, 1):
-                warnings.warn(
-                    "When calling `nn.Module(MetaTensor) on a module traced with "
-                    "`torch.jit.trace`, your version of pytorch returns a "
-                    "`torch.Tensor` instead of a `MetaTensor`. Consider upgrading "
-                    "your pytorch version if this is important to you."
-                )
-                im_conv = im_conv.as_tensor()
         self.check(out, im_conv, ids=False)
 
     def test_pickling(self):
@@ -257,9 +247,6 @@ def test_pickling(self):
             fname = os.path.join(tmp_dir, "im.pt")
             torch.save(m, fname)
             m2 = torch.load(fname)
-            if not isinstance(m2, MetaTensor) and not pytorch_after(1, 8, 1):
-                warnings.warn("Old version of pytorch. pickling converts `MetaTensor` to `torch.Tensor`.")
-                m = m.as_tensor()
         self.check(m2, m, ids=False)
 
     @skip_if_no_cuda
@@ -556,11 +543,10 @@ def test_array_function(self, device="cpu", dtype=float):
         )
         assert_allclose(np.argwhere(c == 1.0).astype(int).tolist(), [[0]])
         assert_allclose(np.concatenate([c, c]), np.asarray([1.0, 2.0, 3.0, 1.0, 2.0, 3.0]))
-        if pytorch_after(1, 8, 1):
-            assert_allclose(c > np.asarray([1.0, 1.0, 1.0]), np.asarray([False, True, True]))
-            assert_allclose(
-                c > torch.as_tensor([1.0, 1.0, 1.0], device=device), torch.as_tensor([False, True, True], device=device)
-            )
+        assert_allclose(c > np.asarray([1.0, 1.0, 1.0]), np.asarray([False, True, True]))
+        assert_allclose(
+            c > torch.as_tensor([1.0, 1.0, 1.0], device=device), torch.as_tensor([False, True, True], device=device)
+        )
 
     @parameterized.expand(TESTS)
     def test_numpy(self, device=None, dtype=None):
diff --git a/tests/test_resize.py b/tests/test_resize.py
index d4c57e2742..0b22c82b75 100644
--- a/tests/test_resize.py
+++ b/tests/test_resize.py
@@ -27,7 +27,6 @@
     SkipIfAtLeastPyTorchVersion,
     assert_allclose,
     is_tf32_env,
-    pytorch_after,
 )
 
 TEST_CASE_0 = [{"spatial_size": 15}, (6, 10, 15)]
@@ -71,7 +70,7 @@ def test_unchange(self):
             ((32, 32), "area", False),
             ((32, 32, 32), "trilinear", True),
             ((256, 256), "bilinear", False),
-            ((256, 256), "nearest-exact" if pytorch_after(1, 11) else "nearest", False),
+            ((256, 256), "nearest-exact", False),
             ((128, 128), "nearest", False),
             ((128, 64), "area", True),  # already in a good shape
         ]
diff --git a/tests/test_resize_with_pad_or_crop.py b/tests/test_resize_with_pad_or_crop.py
index daf257f89f..fe7d85e6b4 100644
--- a/tests/test_resize_with_pad_or_crop.py
+++ b/tests/test_resize_with_pad_or_crop.py
@@ -20,19 +20,19 @@
 from monai.data.meta_tensor import MetaTensor
 from monai.transforms import ResizeWithPadOrCrop
 from monai.transforms.lazy.functional import apply_pending
-from tests.utils import TEST_NDARRAYS_ALL, assert_allclose, pytorch_after
+from tests.utils import TEST_NDARRAYS_ALL, assert_allclose
 
 TEST_CASES = [
     [{"spatial_size": [15, 8, 8], "mode": "constant"}, (3, 8, 8, 4), (3, 15, 8, 8), True],
     [{"spatial_size": [15, 4, -1], "mode": "constant"}, (3, 8, 8, 4), (3, 15, 4, 4), True],
     [
-        {"spatial_size": [15, 4, -1], "mode": "reflect" if pytorch_after(1, 11) else "constant"},
+        {"spatial_size": [15, 4, -1], "mode": "reflect"},
         (3, 8, 8, 4),
         (3, 15, 4, 4),
         True,
     ],
     [
-        {"spatial_size": [-1, -1, -1], "mode": "reflect" if pytorch_after(1, 11) else "constant"},
+        {"spatial_size": [-1, -1, -1], "mode": "reflect"},
         (3, 8, 8, 4),
         (3, 8, 8, 4),
         True,
diff --git a/tests/test_resize_with_pad_or_cropd.py b/tests/test_resize_with_pad_or_cropd.py
index 391e0feb22..914890779a 100644
--- a/tests/test_resize_with_pad_or_cropd.py
+++ b/tests/test_resize_with_pad_or_cropd.py
@@ -22,18 +22,18 @@
 from monai.transforms import ResizeWithPadOrCropd
 from monai.transforms.lazy.functional import apply_pending
 from tests.test_resize_with_pad_or_crop import TESTS_PENDING_MODE
-from tests.utils import TEST_NDARRAYS_ALL, assert_allclose, pytorch_after
+from tests.utils import TEST_NDARRAYS_ALL, assert_allclose
 
 TEST_CASES = [
     [{"keys": "img", "spatial_size": [15, 8, 8], "mode": "constant"}, {"img": np.zeros((3, 8, 8, 4))}, (3, 15, 8, 8)],
     [{"keys": "img", "spatial_size": [15, 4, -1], "mode": "constant"}, {"img": np.zeros((3, 8, 8, 4))}, (3, 15, 4, 4)],
     [
-        {"keys": "img", "spatial_size": [15, 4, -1], "mode": "reflect" if pytorch_after(1, 11) else "constant"},
+        {"keys": "img", "spatial_size": [15, 4, -1], "mode": "reflect"},
         {"img": np.zeros((3, 8, 8, 4))},
         (3, 15, 4, 4),
     ],
     [
-        {"keys": "img", "spatial_size": [-1, -1, -1], "mode": "reflect" if pytorch_after(1, 11) else "constant"},
+        {"keys": "img", "spatial_size": [-1, -1, -1], "mode": "reflect"},
         {"img": np.zeros((3, 8, 8, 4))},
         (3, 8, 8, 4),
     ],
diff --git a/tests/test_swin_unetr.py b/tests/test_swin_unetr.py
index 5b33475c7e..ddc422206a 100644
--- a/tests/test_swin_unetr.py
+++ b/tests/test_swin_unetr.py
@@ -24,21 +24,14 @@
 from monai.networks.nets.swin_unetr import PatchMerging, PatchMergingV2, SwinUNETR, filter_swinunetr
 from monai.networks.utils import copy_model_state
 from monai.utils import optional_import
-from tests.utils import (
-    assert_allclose,
-    pytorch_after,
-    skip_if_downloading_fails,
-    skip_if_no_cuda,
-    skip_if_quick,
-    testing_data_config,
-)
+from tests.utils import assert_allclose, skip_if_downloading_fails, skip_if_no_cuda, skip_if_quick, testing_data_config
 
 einops, has_einops = optional_import("einops")
 
 TEST_CASE_SWIN_UNETR = []
 case_idx = 0
 test_merging_mode = ["mergingv2", "merging", PatchMerging, PatchMergingV2]
-checkpoint_vals = [True, False] if pytorch_after(1, 11) else [False]
+checkpoint_vals = [True, False]
 for attn_drop_rate in [0.4]:
     for in_channels in [1]:
         for depth in [[2, 1, 1, 1], [1, 2, 1, 1]]:
diff --git a/tests/testing_data/integration_answers.py b/tests/testing_data/integration_answers.py
index e02b9ae995..1dbab8e544 100644
--- a/tests/testing_data/integration_answers.py
+++ b/tests/testing_data/integration_answers.py
@@ -70,366 +70,6 @@
             ],
         }
     },
-    {  # test answers for PyTorch 1.12.1
-        "integration_classification_2d": {
-            "losses": [0.776835828070428, 0.1615355300011149, 0.07492854832938523, 0.04591309238865877],
-            "best_metric": 0.9999184380485994,
-            "infer_prop": [1029, 896, 980, 1033, 961, 1046],
-        },
-        "integration_segmentation_3d": {
-            "losses": [
-                0.5428894340991974,
-                0.47331981360912323,
-                0.4482289582490921,
-                0.4452722787857056,
-                0.4289989799261093,
-                0.4359133839607239,
-            ],
-            "best_metric": 0.933259129524231,
-            "infer_metric": 0.9332860708236694,
-            "output_sums": [
-                0.142167581604417,
-                0.15195543400875847,
-                0.1512754523215521,
-                0.13962938779108452,
-                0.18835719348918614,
-                0.16943498693483486,
-                0.1465709827477569,
-                0.16806483607477135,
-                0.1568844609697224,
-                0.17911090857818554,
-                0.16252098157181355,
-                0.16806016936625395,
-                0.14430124467305516,
-                0.11316135548315168,
-                0.16183771025615476,
-                0.2009426314066978,
-                0.1760258010156966,
-                0.09700864497950844,
-                0.1938495370314683,
-                0.20319147575335647,
-                0.19629641404249798,
-                0.20852344793102826,
-                0.16185073630020633,
-                0.13184196857669161,
-                0.1480959525354053,
-                0.14232924377085415,
-                0.23177739882790951,
-                0.16094610375534632,
-                0.14832771888168225,
-                0.10259365443625812,
-                0.11850632233099603,
-                0.1294100326098242,
-                0.11364228279017609,
-                0.15181947897584674,
-                0.16319358155815072,
-                0.1940284526521386,
-                0.22306137879066443,
-                0.18083137638759522,
-                0.1903135237574692,
-                0.07402317520619131,
-            ],
-        },
-        "integration_workflows": {
-            "best_metric": 0.9219646483659745,
-            "infer_metric": 0.921751058101654,
-            "output_sums": [
-                0.14183664321899414,
-                0.1513957977294922,
-                0.13804054260253906,
-                0.13356828689575195,
-                0.18456125259399414,
-                0.16363763809204102,
-                0.14090299606323242,
-                0.16649389266967773,
-                0.15651893615722656,
-                0.17655134201049805,
-                0.16116666793823242,
-                0.1644763946533203,
-                0.14383649826049805,
-                0.11055326461791992,
-                0.16080379486083984,
-                0.19629907608032227,
-                0.17441415786743164,
-                0.053577423095703125,
-                0.19043779373168945,
-                0.19904804229736328,
-                0.19526052474975586,
-                0.20304107666015625,
-                0.16030025482177734,
-                0.13170623779296875,
-                0.15118932723999023,
-                0.13686418533325195,
-                0.22668886184692383,
-                0.1611471176147461,
-                0.1472463607788086,
-                0.10427379608154297,
-                0.11962461471557617,
-                0.1305704116821289,
-                0.11204910278320312,
-                0.15171337127685547,
-                0.15962505340576172,
-                0.18976259231567383,
-                0.21649456024169922,
-                0.17761802673339844,
-                0.18516874313354492,
-                0.03636503219604492,
-            ],
-            "best_metric_2": 0.9219559609889985,
-            "infer_metric_2": 0.9217371672391892,
-            "output_sums_2": [
-                0.14187288284301758,
-                0.15140819549560547,
-                0.13802719116210938,
-                0.1335887908935547,
-                0.18454980850219727,
-                0.1636652946472168,
-                0.14091157913208008,
-                0.16653108596801758,
-                0.15651702880859375,
-                0.17658615112304688,
-                0.1611957550048828,
-                0.16448307037353516,
-                0.14385128021240234,
-                0.1105203628540039,
-                0.16085100173950195,
-                0.19626951217651367,
-                0.17442035675048828,
-                0.053586483001708984,
-                0.19042730331420898,
-                0.1990523338317871,
-                0.1952815055847168,
-                0.20303773880004883,
-                0.16034317016601562,
-                0.13172531127929688,
-                0.15118741989135742,
-                0.1368694305419922,
-                0.22667837142944336,
-                0.16119050979614258,
-                0.14726591110229492,
-                0.10426473617553711,
-                0.11961841583251953,
-                0.13054800033569336,
-                0.11203193664550781,
-                0.15172529220581055,
-                0.15963029861450195,
-                0.18975019454956055,
-                0.21646499633789062,
-                0.17763566970825195,
-                0.18517112731933594,
-                0.03638744354248047,
-            ],
-        },
-    },
-    {  # test answers for cuda 10.x
-        "integration_classification_2d": {
-            "losses": [0.777176220515731, 0.16019743723664315, 0.07480076164197011, 0.045643698364780966],
-            "best_metric": 0.9999418774120775,
-            "infer_prop": [1030, 897, 980, 1033, 960, 1048],
-        },
-        "integration_segmentation_3d": {
-            "losses": [
-                0.5326887160539627,
-                0.4685510128736496,
-                0.46245276033878324,
-                0.4411882758140564,
-                0.4198471873998642,
-                0.43021280467510226,
-            ],
-            "best_metric": 0.931993305683136,
-            "infer_metric": 0.9326668977737427,
-            "output_sums": [
-                0.1418775228871769,
-                0.15188869120317386,
-                0.15140863737688195,
-                0.1396146850007127,
-                0.18784343811575696,
-                0.16909487431163164,
-                0.14649608249452073,
-                0.1677767130878611,
-                0.1568122289811143,
-                0.17874181729735056,
-                0.16213703658980205,
-                0.16754335171970686,
-                0.14444824920997243,
-                0.11432402622850306,
-                0.16143210936221247,
-                0.20055289634107482,
-                0.17543571757219317,
-                0.09920729163334538,
-                0.19297325815057875,
-                0.2023200127892273,
-                0.1956677579845722,
-                0.20774045016425718,
-                0.16193278944159428,
-                0.13174198906539808,
-                0.14830508550670007,
-                0.14241105864278342,
-                0.23090631643085724,
-                0.16056153813499532,
-                0.1480353269419819,
-                0.10318719171632634,
-                0.11867462580989198,
-                0.12997011485830187,
-                0.11401220332210203,
-                0.15242746700662088,
-                0.1628489107974574,
-                0.19327235354175412,
-                0.22184902863377548,
-                0.18028049625972334,
-                0.18958059106892552,
-                0.07884601267057013,
-            ],
-        },
-        "integration_workflows": {
-            "best_metric": 0.9217087924480438,
-            "infer_metric": 0.9214379042387009,
-            "output_sums": [
-                0.14209461212158203,
-                0.15126705169677734,
-                0.13800382614135742,
-                0.1338181495666504,
-                0.1850571632385254,
-                0.16372442245483398,
-                0.14059066772460938,
-                0.16674423217773438,
-                0.15653657913208008,
-                0.17690563201904297,
-                0.16154909133911133,
-                0.16521310806274414,
-                0.14388608932495117,
-                0.1103353500366211,
-                0.1609959602355957,
-                0.1967010498046875,
-                0.1746964454650879,
-                0.05329275131225586,
-                0.19098854064941406,
-                0.19976520538330078,
-                0.19576644897460938,
-                0.20346736907958984,
-                0.1601848602294922,
-                0.1316051483154297,
-                0.1511220932006836,
-                0.13670969009399414,
-                0.2276287078857422,
-                0.1611800193786621,
-                0.14751672744750977,
-                0.10413789749145508,
-                0.11944007873535156,
-                0.1305546760559082,
-                0.11204719543457031,
-                0.15145111083984375,
-                0.16007614135742188,
-                0.1904129981994629,
-                0.21741962432861328,
-                0.17812013626098633,
-                0.18587207794189453,
-                0.03605222702026367,
-            ],
-            "best_metric_2": 0.9210659921169281,
-            "infer_metric_2": 0.9208109736442566,
-            "output_sums_2": [
-                0.14227628707885742,
-                0.1515035629272461,
-                0.13819408416748047,
-                0.13402271270751953,
-                0.18525266647338867,
-                0.16388607025146484,
-                0.14076614379882812,
-                0.16694307327270508,
-                0.15677356719970703,
-                0.1771831512451172,
-                0.16172313690185547,
-                0.1653728485107422,
-                0.14413118362426758,
-                0.11057281494140625,
-                0.16121912002563477,
-                0.19680166244506836,
-                0.1748638153076172,
-                0.053426265716552734,
-                0.19117307662963867,
-                0.19996356964111328,
-                0.1959366798400879,
-                0.20363712310791016,
-                0.16037797927856445,
-                0.13180780410766602,
-                0.1513657569885254,
-                0.13686084747314453,
-                0.2277364730834961,
-                0.16137409210205078,
-                0.1476879119873047,
-                0.10438394546508789,
-                0.11967992782592773,
-                0.13080739974975586,
-                0.11226606369018555,
-                0.15168476104736328,
-                0.1602616310119629,
-                0.190582275390625,
-                0.21756458282470703,
-                0.17825984954833984,
-                0.18604803085327148,
-                0.036206722259521484,
-            ],
-        },
-    },
-    {  # test answers for PyTorch 1.9
-        "integration_workflows": {
-            "output_sums_2": [
-                0.14213180541992188,
-                0.15153264999389648,
-                0.13801145553588867,
-                0.1338348388671875,
-                0.18515968322753906,
-                0.16404008865356445,
-                0.14110612869262695,
-                0.16686391830444336,
-                0.15673542022705078,
-                0.1772594451904297,
-                0.16174745559692383,
-                0.16518878936767578,
-                0.1440296173095703,
-                0.11033201217651367,
-                0.1611781120300293,
-                0.19660568237304688,
-                0.17468547821044922,
-                0.053053855895996094,
-                0.1909656524658203,
-                0.19952869415283203,
-                0.1957845687866211,
-                0.2034916877746582,
-                0.16042661666870117,
-                0.13193607330322266,
-                0.15104389190673828,
-                0.13695430755615234,
-                0.22720861434936523,
-                0.16157913208007812,
-                0.14759159088134766,
-                0.10379791259765625,
-                0.11937189102172852,
-                0.1306462287902832,
-                0.11205482482910156,
-                0.15182113647460938,
-                0.16006708145141602,
-                0.19011592864990234,
-                0.21713829040527344,
-                0.17794132232666016,
-                0.18584394454956055,
-                0.03577899932861328,
-            ]
-        },
-        "integration_segmentation_3d": {  # for the mixed readers
-            "losses": [
-                0.5645154356956482,
-                0.4984356611967087,
-                0.472334086894989,
-                0.47419720590114595,
-                0.45881829261779783,
-                0.43097741305828097,
-            ],
-            "best_metric": 0.9325698614120483,
-            "infer_metric": 0.9326590299606323,
-        },
-    },
     {  # test answers for PyTorch 1.13
         "integration_workflows": {
             "output_sums_2": [