diff --git a/installer.py b/installer.py
index 05bbeb5bb..c04fecead 100644
--- a/installer.py
+++ b/installer.py
@@ -375,10 +375,10 @@ def check_torch():
         os.environ.setdefault('NEOReadDebugKeys', '1')
         os.environ.setdefault('ClDeviceGlobalMemSizeAvailablePercent', '100')
         if "linux" in sys.platform:
-            torch_command = os.environ.get('TORCH_COMMAND', 'torch==2.0.1a0 torchvision==0.15.2a0 intel_extension_for_pytorch==2.0.110+xpu -f https://developer.intel.com/ipex-whl-stable-xpu')
+            torch_command = os.environ.get('TORCH_COMMAND', 'torch==2.0.1a0 torchvision==0.15.2a0 intel_extension_for_pytorch==2.0.110+xpu openvino==2023.1.0.dev20230728 -f https://developer.intel.com/ipex-whl-stable-xpu')
             os.environ.setdefault('TENSORFLOW_PACKAGE', 'tensorflow==2.13.0 intel-extension-for-tensorflow[gpu]')
         else:
-            torch_command = os.environ.get('TORCH_COMMAND', 'torch==2.0.0a0 torchvision==0.15.2a0 intel_extension_for_pytorch==2.0.110+gitba7f6c1 -f https://developer.intel.com/ipex-whl-stable-xpu')
+            torch_command = os.environ.get('TORCH_COMMAND', 'torch==2.0.0a0 torchvision==0.15.1 intel_extension_for_pytorch==2.0.110+gitba7f6c1 openvino==2023.1.0.dev20230728 -f https://developer.intel.com/ipex-whl-stable-xpu')
     else:
         machine = platform.machine()
         if sys.platform == 'darwin':
diff --git a/modules/ipex_specific/__init__.py b/modules/ipex_specific/__init__.py
index ecb72641f..f8fdca2eb 100644
--- a/modules/ipex_specific/__init__.py
+++ b/modules/ipex_specific/__init__.py
@@ -86,3 +86,7 @@ def ipex_init():
 
     ipex_hijacks()
     ipex_diffusers()
+    try:
+        from .openvino import openvino_fx
+    except Exception:
+        pass
diff --git a/modules/ipex_specific/hijacks.py b/modules/ipex_specific/hijacks.py
index 32e075204..05419f426 100644
--- a/modules/ipex_specific/hijacks.py
+++ b/modules/ipex_specific/hijacks.py
@@ -8,6 +8,40 @@ def ipex_no_cuda(orig_func, *args, **kwargs): # pylint: disable=redefined-outer-
     orig_func(*args, **kwargs)
     torch.cuda.is_available = torch.xpu.is_available
 
+#FP32:
+original_linear_forward = torch.nn.modules.Linear.forward
+def linear_forward(self, input):
+    if input.dtype != self.weight.data.dtype:
+        return original_linear_forward(self, input.to(self.weight.data.dtype))
+    else:
+        return original_linear_forward(self, input)
+
+#Embedding BF16
+original_torch_cat = torch.cat
+def torch_cat(input, *args, **kwargs):
+    if len(input) == 3 and (input[0].dtype != input[1].dtype or input[2].dtype != input[1].dtype):
+        return original_torch_cat([input[0].to(input[1].dtype), input[1], input[2].to(input[1].dtype)], *args, **kwargs)
+    else:
+        return original_torch_cat(input, *args, **kwargs)
+
+original_conv2d = torch.nn.functional.conv2d
+#Diffusers BF16:
+def conv2d(input, weight, *args, **kwargs):
+    if input.dtype != weight.data.dtype:
+        return original_conv2d(input.to(weight.data.dtype), weight, *args, **kwargs)
+    else:
+        return original_conv2d(input, weight, *args, **kwargs)
+
+original_interpolate = torch.nn.functional.interpolate
+#Latent antialias:
+def interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False):
+    if antialias:
+        return original_interpolate(input.to("cpu"), size=size, scale_factor=scale_factor, mode=mode,
+        align_corners=align_corners, recompute_scale_factor=recompute_scale_factor, antialias=antialias).to(shared.device)
+    else:
+        return original_interpolate(input, size=size, scale_factor=scale_factor, mode=mode,
+        align_corners=align_corners, recompute_scale_factor=recompute_scale_factor, antialias=antialias)
+
 def ipex_hijacks():
     #Libraries that blindly uses cuda:
     #Adetailer:
@@ -36,10 +70,6 @@ def ipex_hijacks():
     CondFunc('torch.nn.modules.GroupNorm.forward',
         lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
         lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
-    #FP32:
-    CondFunc('torch.nn.modules.Linear.forward',
-        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
-        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
     #Embedding FP32:
     CondFunc('torch.bmm',
         lambda orig_func, input, mat2, *args, **kwargs: orig_func(input, mat2.to(input.dtype), *args, **kwargs),
@@ -50,14 +80,6 @@ def ipex_hijacks():
         orig_func(input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs),
         lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
         input.dtype != weight.data.dtype and weight is not None)
-    #Embedding BF16
-    CondFunc('torch.cat',
-        lambda orig_func, input, *args, **kwargs: orig_func([input[0].to(input[1].dtype), input[1], input[2].to(input[1].dtype)], *args, **kwargs),
-        lambda orig_func, input, *args, **kwargs: len(input) == 3 and (input[0].dtype != input[1].dtype or input[2].dtype != input[1].dtype))
-    #Diffusers BF16:
-    CondFunc('torch.nn.functional.conv2d',
-        lambda orig_func, input, weight, *args, **kwargs: orig_func(input.to(weight.data.dtype), weight, *args, **kwargs),
-        lambda orig_func, input, weight, *args, **kwargs: input.dtype != weight.data.dtype)
 
     #Functions that does not work with the XPU:
     #UniPC:
@@ -68,10 +90,6 @@ def ipex_hijacks():
     CondFunc('torch.Generator',
         lambda orig_func, device: torch.xpu.Generator(device),
         lambda orig_func, device: device != torch.device("cpu") and device != "cpu")
-    #Latent antialias:
-    CondFunc('torch.nn.functional.interpolate',
-        lambda orig_func, input, *args, **kwargs: orig_func(input.to("cpu"), *args, **kwargs).to(shared.device),
-        lambda orig_func, input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False: antialias)
     #Diffusers Float64 (ARC GPUs doesn't support double or Float64):
     if not torch.xpu.has_fp64_dtype():
         CondFunc('torch.from_numpy',
@@ -89,3 +107,9 @@ def ipex_hijacks():
         weight if weight is not None else torch.ones(input.size()[1], device=shared.device),
         bias if bias is not None else torch.zeros(input.size()[1], device=shared.device), *args, **kwargs),
         lambda orig_func, input, *args, **kwargs: input.device != torch.device("cpu"))
+
+    #Functions that make compile mad with CondFunc:
+    torch.nn.modules.Linear.forward = linear_forward
+    torch.cat = torch_cat
+    torch.nn.functional.conv2d = conv2d
+    torch.nn.functional.interpolate = interpolate
diff --git a/modules/ipex_specific/openvino.py b/modules/ipex_specific/openvino.py
new file mode 100644
index 000000000..5101c7d8e
--- /dev/null
+++ b/modules/ipex_specific/openvino.py
@@ -0,0 +1,33 @@
+import os
+import torch
+import intel_extension_for_pytorch as ipex
+from openvino.frontend.pytorch.torchdynamo.execute import execute
+from openvino.frontend.pytorch.torchdynamo.partition import Partitioner
+from torch._dynamo.backends.common import fake_tensor_unsupported
+from torch._dynamo.backends.registry import register_backend
+from torch._inductor.compile_fx import compile_fx
+from torch.fx.experimental.proxy_tensor import make_fx
+
+class ModelState:
+    def __init__(self):
+        self.recompile = 1
+        self.partition_id = 0
+
+model_state = ModelState()
+
+@register_backend
+@fake_tensor_unsupported
+def openvino_fx(subgraph, example_inputs):
+    if os.getenv("OPENVINO_TORCH_BACKEND_DEVICE") is None:
+        os.environ.setdefault("OPENVINO_TORCH_BACKEND_DEVICE", "GPU")
+
+    model = make_fx(subgraph)(*example_inputs)
+    with torch.no_grad():
+        model.eval()
+    partitioner = Partitioner()
+    compiled_model = partitioner.make_partitions(model)
+
+    def _call(*args):
+        res = execute(compiled_model, *args, executor="openvino")
+        return res
+    return _call
diff --git a/modules/shared.py b/modules/shared.py
index 945f2a27f..de66b56c8 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -384,7 +384,7 @@ options_templates.update(options_section(('cuda', "Compute Settings"), {
     # "cuda_allow_tf32": OptionInfo(True, "Allow TF32 math ops"),
     # "cuda_allow_tf16_reduced": OptionInfo(True, "Allow TF16 reduced precision math ops"),
     "cuda_compile": OptionInfo(False, "Enable model compile (experimental)"),
-    "cuda_compile_backend": OptionInfo("none", "Model compile backend (experimental)", gr.Radio, lambda: {"choices": ['none', 'inductor', 'cudagraphs', 'aot_ts_nvfuser', 'hidet', 'ipex']}),
+    "cuda_compile_backend": OptionInfo("none", "Model compile backend (experimental)", gr.Radio, lambda: {"choices": ['none', 'inductor', 'cudagraphs', 'aot_ts_nvfuser', 'hidet', 'ipex', 'openvino_fx']}),
     "cuda_compile_mode": OptionInfo("default", "Model compile mode (experimental)", gr.Radio, lambda: {"choices": ['default', 'reduce-overhead', 'max-autotune']}),
     "cuda_compile_fullgraph": OptionInfo(False, "Model compile fullgraph"),
     "cuda_compile_verbose": OptionInfo(False, "Model compile verbose mode"),
diff --git a/webui.sh b/webui.sh
index 38fc189b1..59f235aac 100755
--- a/webui.sh
+++ b/webui.sh
@@ -96,10 +96,6 @@ if [[ ! -z "${ACCELERATE}" ]] && [ ${ACCELERATE}="True" ] && [ -x "$(command -v
 then
     echo "Launching accelerate launch.py..."
     exec accelerate launch --num_cpu_threads_per_process=6 launch.py "$@"
-elif [[ "$@" == *"--use-ipex"* ]] && [[ -z "${first_launch}" ]] && [ -x "$(command -v ipexrun)" ] && [ -x "$(command -v sycl-ls)" ]
-then
-    echo "Launching ipexrun launch.py..."
-    exec ipexrun --multi-task-manager 'taskset' launch.py "$@"
 else
     echo "Launching launch.py..."
     exec "${python_cmd}" launch.py "$@"