diff --git a/py/torch_tensorrt/dynamo/conversion/__init__.py b/py/torch_tensorrt/dynamo/conversion/__init__.py
index 4536ff0e7b..9cbfff950e 100644
--- a/py/torch_tensorrt/dynamo/conversion/__init__.py
+++ b/py/torch_tensorrt/dynamo/conversion/__init__.py
@@ -1,4 +1,5 @@
 from ._TRTInterpreter import *  # noqa: F403
 from .aten_ops_converters import *  # noqa: F403
 from .conversion import *  # noqa: F403
+from .op_evaluators import *  # noqa: F403
 from .truncate_long_and_double import repair_long_or_double_inputs
diff --git a/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py b/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py
index 8d1d9b7ecf..75a7782354 100644
--- a/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py
+++ b/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py
@@ -1,5 +1,4 @@
 import logging
-import operator
 from typing import Any, Dict, Optional, Sequence, Tuple, Union
 
 import tensorrt as trt
@@ -406,24 +405,6 @@ def aten_ops_to_copy_dtype(
     )
 
 
-@dynamo_tensorrt_converter(operator.getitem)
-def operator_getitem(
-    network: TRTNetwork,
-    target: Target,
-    args: Tuple[Argument, ...],
-    kwargs: Dict[str, Argument],
-    name: str,
-) -> Union[TRTTensor, Sequence[TRTTensor]]:
-    return impl.evaluators.getitem(
-        network,
-        target,
-        SourceIR.ATEN,
-        name,
-        args[0],
-        args[1],
-    )
-
-
 @dynamo_tensorrt_converter(torch.ops.aten.clone.default)
 def aten_ops_clone(
     network: TRTNetwork,
@@ -432,7 +413,7 @@ def aten_ops_clone(
     kwargs: Dict[str, Argument],
     name: str,
 ) -> Union[TRTTensor, Sequence[TRTTensor]]:
-    return impl.evaluators.clone(
+    return impl.cast.clone(
         network,
         target,
         SourceIR.ATEN,
diff --git a/py/torch_tensorrt/dynamo/conversion/converter_utils.py b/py/torch_tensorrt/dynamo/conversion/converter_utils.py
index bbb57b9da7..d29393b18e 100644
--- a/py/torch_tensorrt/dynamo/conversion/converter_utils.py
+++ b/py/torch_tensorrt/dynamo/conversion/converter_utils.py
@@ -4,7 +4,7 @@
 
 import tensorrt as trt
 import torch
-from torch.fx.node import Target, _get_qualified_name
+from torch.fx.node import Target
 from torch_tensorrt.fx.converters.converter_utils import (
     Frameworks,
     unified_dtype_converter,
@@ -12,6 +12,7 @@
 from torch_tensorrt.fx.types import TRTDataType, TRTNetwork, TRTTensor
 
 from .._SourceIR import SourceIR
+from .converter_registry import ConverterRegistry
 
 _LOGGER: logging.Logger = logging.getLogger(__name__)
 
@@ -94,15 +95,12 @@ def cast_trt_tensor(
 
     if input_val.dtype != trt_dtype:
         source_ir = source_ir if source_ir is not None else SourceIR.UNKNOWN
-        target_name = (
-            f"{source_ir}_ops{'.' + target if target else ''}"
-            if (isinstance(target, str))
-            else f"{source_ir}_ops.{_get_qualified_name(target)}"
-        )
+        target_str = ConverterRegistry.qualified_name_or_str(target)
+        target_name = f"{source_ir}_ops{'.' + target_str if target_str else ''}"
 
         identity_layer = network.add_identity(input_val)
         identity_layer.set_output_type(0, trt_dtype)
-        identity_layer.name = f"Cast ITensor {input_val.name} from {input_val.dtype} to {trt_dtype} -{name}-[{target_name}]-[{name}]"
+        identity_layer.name = f"Cast ITensor {input_val.name} from {input_val.dtype} to {trt_dtype} - [{target_name}]-[{name}]"
         return identity_layer.get_output(0)
     else:
         return input_val
diff --git a/py/torch_tensorrt/dynamo/conversion/impl/__init__.py b/py/torch_tensorrt/dynamo/conversion/impl/__init__.py
index 611dc630fa..8f7ab1badc 100644
--- a/py/torch_tensorrt/dynamo/conversion/impl/__init__.py
+++ b/py/torch_tensorrt/dynamo/conversion/impl/__init__.py
@@ -6,7 +6,6 @@
     condition,
     elementwise,
     embedding,
-    evaluators,
     matmul,
     normalization,
     permutation,
diff --git a/py/torch_tensorrt/dynamo/conversion/impl/cast.py b/py/torch_tensorrt/dynamo/conversion/impl/cast.py
index 68899de766..0c55731169 100644
--- a/py/torch_tensorrt/dynamo/conversion/impl/cast.py
+++ b/py/torch_tensorrt/dynamo/conversion/impl/cast.py
@@ -1,3 +1,4 @@
+import logging
 from typing import Optional
 
 from torch.fx.node import Target
@@ -5,6 +6,8 @@
 from torch_tensorrt.dynamo.conversion.converter_utils import cast_trt_tensor
 from torch_tensorrt.fx.types import TRTDataType, TRTNetwork, TRTTensor
 
+LOGGER: logging.Logger = logging.getLogger(__name__)
+
 
 def to_copy(
     network: TRTNetwork,
@@ -21,3 +24,20 @@ def to_copy(
 
     casted_tensor = cast_trt_tensor(network, input, dtype, name, target, source_ir)
     return casted_tensor
+
+
+def clone(
+    network: TRTNetwork,
+    target: Target,
+    source_ir: Optional[SourceIR],
+    name: str,
+    input: TRTTensor,
+) -> TRTTensor:
+    if not isinstance(input, TRTTensor):
+        raise RuntimeError(
+            f"clone received input {input} that is not a TensorRT ITensor"
+        )
+
+    LOGGER.debug(f"Evaluating clone on object with name: {name}")
+
+    return input
diff --git a/py/torch_tensorrt/dynamo/conversion/impl/evaluators.py b/py/torch_tensorrt/dynamo/conversion/impl/evaluators.py
deleted file mode 100644
index cb61fb6158..0000000000
--- a/py/torch_tensorrt/dynamo/conversion/impl/evaluators.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import logging
-import operator
-from typing import Optional, Sequence
-
-from torch.fx.node import Target
-from torch_tensorrt.dynamo._SourceIR import SourceIR
-from torch_tensorrt.fx.types import TRTNetwork, TRTTensor
-
-LOGGER: logging.Logger = logging.getLogger(__name__)
-
-
-def getitem(
-    network: TRTNetwork,
-    target: Target,
-    source_ir: Optional[SourceIR],
-    name: str,
-    input: Sequence[TRTTensor],
-    index: int,
-) -> TRTTensor:
-    LOGGER.debug(f"Evaluating getitem on object with name: {name}")
-
-    # Directly index the input sequence and return the value
-    return operator.getitem(input, index)
-
-
-def clone(
-    network: TRTNetwork,
-    target: Target,
-    source_ir: Optional[SourceIR],
-    name: str,
-    input: TRTTensor,
-) -> TRTTensor:
-    if not isinstance(input, TRTTensor):
-        raise RuntimeError(
-            f"clone received input {input} that is not a TensorRT ITensor"
-        )
-
-    LOGGER.debug(f"Evaluating clone on object with name: {name}")
-
-    return input
diff --git a/py/torch_tensorrt/dynamo/conversion/op_evaluators.py b/py/torch_tensorrt/dynamo/conversion/op_evaluators.py
new file mode 100644
index 0000000000..a546e34305
--- /dev/null
+++ b/py/torch_tensorrt/dynamo/conversion/op_evaluators.py
@@ -0,0 +1,32 @@
+import logging
+import operator
+from typing import Dict, Sequence, Tuple, Union
+
+from torch.fx.node import Argument, Node, Target
+from torch_tensorrt.fx.types import TRTNetwork, TRTTensor
+
+from .converter_registry import ConverterRegistry, dynamo_tensorrt_converter
+
+_LOGGER: logging.Logger = logging.getLogger(__name__)
+
+
+def getitem_validator(getitem_node: Node) -> bool:
+    from torch_tensorrt.dynamo.conversion.converter_registry import DYNAMO_CONVERTERS
+
+    # Getitem nodes can only be converted if their parent node also can
+    return getitem_node.args[0] in DYNAMO_CONVERTERS
+
+
+# TODO: Subsequent evaluators should be registered here with their own validators
+@dynamo_tensorrt_converter(operator.getitem, capability_validator=getitem_validator)
+def generic_evaluator(
+    network: TRTNetwork,
+    target: Target,
+    args: Tuple[Argument, ...],
+    kwargs: Dict[str, Argument],
+    name: str,
+) -> Union[TRTTensor, Sequence[TRTTensor]]:
+    _LOGGER.debug(
+        f"Evaluating {ConverterRegistry.qualified_name_or_str(target)} on object with name: {name}"
+    )
+    return target(*args)
diff --git a/tests/py/dynamo/converters/test_casts.py b/tests/py/dynamo/converters/test_casts.py
index 4bb05ef463..3a4fd65610 100644
--- a/tests/py/dynamo/converters/test_casts.py
+++ b/tests/py/dynamo/converters/test_casts.py
@@ -5,6 +5,36 @@
 from torch_tensorrt.dynamo.conversion import UnsupportedOperatorException
 
 
+class TestCloneConverter(DispatchTestCase):
+    def test_clone_contiguous(self):
+        class Clone(nn.Module):
+            def forward(self, x):
+                y = torch.clone(x, memory_format=torch.contiguous_format)
+                return y + 1
+
+        inputs = [torch.randn((1, 3, 10))]
+        self.run_test(
+            Clone(),
+            inputs,
+            expected_ops={torch.ops.aten.clone.default},
+            disable_passes=True,
+        )
+
+    def test_clone_regular(self):
+        class Clone(nn.Module):
+            def forward(self, x):
+                y = torch.clone(x)
+                return y + 1
+
+        inputs = [torch.randn((8, 2, 10))]
+        self.run_test(
+            Clone(),
+            inputs,
+            expected_ops={torch.ops.aten.clone.default},
+            disable_passes=True,
+        )
+
+
 class TestToCopyConverter(DispatchTestCase):
     def test_to_copy_half(self):
         class ToCopyHalf(nn.Module):
diff --git a/tests/py/dynamo/converters/test_evaluators.py b/tests/py/dynamo/converters/test_evaluators.py
index cf42009495..64dd303727 100644
--- a/tests/py/dynamo/converters/test_evaluators.py
+++ b/tests/py/dynamo/converters/test_evaluators.py
@@ -7,36 +7,6 @@
 from torch.testing._internal.common_utils import run_tests
 
 
-class TestCloneConverter(DispatchTestCase):
-    def test_clone_contiguous(self):
-        class Clone(nn.Module):
-            def forward(self, x):
-                y = torch.clone(x, memory_format=torch.contiguous_format)
-                return y + 1
-
-        inputs = [torch.randn((1, 3, 10))]
-        self.run_test(
-            Clone(),
-            inputs,
-            expected_ops={torch.ops.aten.clone.default},
-            disable_passes=True,
-        )
-
-    def test_clone_regular(self):
-        class Clone(nn.Module):
-            def forward(self, x):
-                y = torch.clone(x)
-                return y + 1
-
-        inputs = [torch.randn((8, 2, 10))]
-        self.run_test(
-            Clone(),
-            inputs,
-            expected_ops={torch.ops.aten.clone.default},
-            disable_passes=True,
-        )
-
-
 # TODO: Switch this test back to self.run_test once an implementation exists
 # for a converter that returns a list, such as aten.split
 @unittest.skip("Pending aten.split converter. Currently tested by E2E")
diff --git a/tests/py/dynamo/models/test_models.py b/tests/py/dynamo/models/test_models.py
index c8f730e2e6..50d7fcbbd9 100644
--- a/tests/py/dynamo/models/test_models.py
+++ b/tests/py/dynamo/models/test_models.py
@@ -27,7 +27,6 @@ def test_resnet18(ir):
         "ir": ir,
         "pass_through_build_failures": True,
         "optimization_level": 1,
-        "min_block_size": 10,
         "ir": "torch_compile",
     }
 
@@ -176,7 +175,6 @@ def test_resnet18_half(ir):
         "ir": ir,
         "pass_through_build_failures": True,
         "optimization_level": 1,
-        "min_block_size": 10,
         "ir": "torch_compile",
     }