Exported into ONNX with Dynamic Shapes

The following script shows the exported program for many short cases and various way to retrieve the torch.fx.Graph equivalent to the original model. The tested scenarios are described at Tested Scenarios.

<<<

import inspect
import textwrap
import pandas
from experimental_experiment.torch_interpreter.eval import discover, run_exporter
from experimental_experiment.ext_test_case import unit_test_going
from experimental_experiment.helpers import pretty_onnx

cases = discover()
print()
print(":ref:`Summary <lod-summary-exported-program>`")
print()
sorted_cases = sorted(cases.items())
if unit_test_going():
    sorted_cases = sorted_cases[:3]
for name, cls_model in sorted_cases:
    print(f"* :ref:`{name} <lod-model-case-export-{name}>`")
print()

obs = []
for name, cls_model in sorted(cases.items()):
    print()
    print(f".. _lod-model-case-export-{name}:")
    print()
    print(name)
    print("=" * len(name))
    print()
    print("forward")
    print("+++++++")
    print()
    print("::")
    print()
    print(
        textwrap.indent(textwrap.dedent(inspect.getsource(cls_model.forward)), "    ")
    )
    print()
    for exporter in (
        "custom-fallback",
        "custom-dec",
        "custom-tracing",
        "dynamo-ir",
        "script",
    ):
        expname = exporter.replace("export-", "")
        print()
        print(expname)
        print("+" * len(expname))
        print()
        res = run_exporter(exporter, cls_model, True, quiet=True)
        case_ref = f":ref:`{name} <lod-model-case-export-{name}>`"
        if "exported" in res:
            print("::")
            print()
            print(textwrap.indent(pretty_onnx(res["onnx"]), "    "))
            print()
            obs.append(dict(case=case_ref, error="", exporter=exporter))
        else:
            print("**FAILED**")
            print()
            print("::")
            print()
            print(textwrap.indent(str(res["error"]), "    "))
            print()
            obs.append(dict(case=case_ref, error="FAIL", exporter=exporter))

print()
print(".. _lod-summary-exported-program:")
print()
print("Summary")
print("+++++++")
print()
df = pandas.DataFrame(obs)
piv = df.pivot(index="case", columns="exporter", values="error")
print(piv.to_markdown(tablefmt="rst"))
print()

>>>

Summary

• AtenAsStrided

• AtenInterpolate

• AtenNonZero

• AtenNonZeroTuple

• AtenRollPos

• AtenRollRelu

• BuildInIsInstance

• BuildInLen

• ComplexPolar

• ControlFlowCond

• ControlFlowCond2Inputs

• ControlFlowCond2Outputs

• ControlFlowCondConstant

• ControlFlowCondNestedModule

• ControlFlowCondNonZero

• ControlFlowNestCond

• ControlFlowScan

• ControlFlowScan2Carried

• ControlFlowScanCDist

• ControlFlowScanCDist2

• ControlFlowScanCDistXY

• CreateFromShape

• CreateFromShapeThroughFunction

• CropLastDimensionWithTensorContent

• CropLastDimensionWithTensorShape

• InplaceAdd

• InplaceAdd2

• InplaceAdd_Mul

• InplaceCloneAdd_

• InplaceSetItemEllipsis_1

• InplaceSetItemEllipsis_2

• InplaceSetItemMask

• InplaceSetItemSquare

• InplaceSetItemSquareAdd

• InplaceSetItemSquareAdd2

• SignatureFloat1

• SignatureInt1

• SignatureInt2

• SignatureListFixedLength

• SignatureListFixedWithNone

• SignatureListVariableLength

• SignatureShapeAsIndex

• TypeBFloat16

AtenAsStrided

forward

def forward(self, x):
    y = torch.as_strided(x, (2, 2, 8, 4), (128, 8, 16, 1))
    return y

custom-fallback

FAILED

The implementation is still incorrect, x='x', shape=('batch', 2, 8, 8), size=[2, 2, 8, 4], stride=[128, 8, 16, 1], storage_offset=None
--DEBUG--
[GraphBuilder-YDK] Message starts, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.
--CONSTRAINTS--
    batch = {'s0'}
    s0 = {'batch'}
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
   s0 = 's0'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={'s0': 'batch'}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'x': 1}
_known_shapes={'x': ('batch', 2, 8, 8)}
_known_value_shape={}
_known_constants=[]
_known_ranks={}
--TORCH-USERS--
    as_strided -> {output}
    x -> {as_strided}
--TORCH-SHAPES--
    x: ('run_node', ('', ('val', torch.float32, torch.Size([s0, 2, 8, 8])))) --- 1:4:('batch', 2, 8, 8):
    as_strided: ('run_node', ('', ('val', torch.float32, torch.Size([2, 2, 8, 4])))) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(fallback=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %as_strided : [num_users=1] = call_function[target=torch.ops.aten.as_strided.default](args = (%x, [2, 2, 8, 4], [128, 8, 16, 1]), kwargs = {})
    return (as_strided,)
-- process.progress --
node 1/3 target=aten.as_strided.default
--
[GraphBuilder-YDK.make_tensor_input] x[1:batchx2x8x8]
[GraphBuilder-YDK] Message completed, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.

custom-dec

FAILED

The implementation is still incorrect, x='x', shape=('batch', 2, 8, 8), size=[2, 2, 8, 4], stride=[128, 8, 16, 1], storage_offset=None
--DEBUG--
[GraphBuilder-BRS] Message starts, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.
--CONSTRAINTS--
    batch = {'s0'}
    s0 = {'batch'}
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
   s0 = 's0'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={'s0': 'batch'}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'x': 1}
_known_shapes={'x': ('batch', 2, 8, 8)}
_known_value_shape={}
_known_constants=[]
_known_ranks={}
--TORCH-USERS--
    as_strided -> {output}
    x -> {as_strided}
--TORCH-SHAPES--
    x: ('run_node', ('', ('val', torch.float32, torch.Size([s0, 2, 8, 8])))) --- 1:4:('batch', 2, 8, 8):
    as_strided: ('run_node', ('', ('val', torch.float32, torch.Size([2, 2, 8, 4])))) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(decomposition_table='default')
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %as_strided : [num_users=1] = call_function[target=torch.ops.aten.as_strided.default](args = (%x, [2, 2, 8, 4], [128, 8, 16, 1]), kwargs = {})
    return (as_strided,)
-- process.progress --
node 1/3 target=aten.as_strided.default
--
[GraphBuilder-BRS.make_tensor_input] x[1:batchx2x8x8]
[GraphBuilder-BRS] Message completed, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.

custom-tracing

FAILED

The implementation is still incorrect, x='x', shape=('batch', 2, 8, 8), size=(2, 2, 8, 4), stride=(128, 8, 16, 1), storage_offset=None
--DEBUG--
[GraphBuilder-JMU] Message starts, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'x': 1}
_known_shapes={'x': ('batch', 2, 8, 8)}
_known_value_shape={}
_known_constants=[]
_known_ranks={}
--TORCH-USERS--
    as_strided -> {output}
    x -> {as_strided}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([2, 2, 8, 8])), '')) --- 1:4:('batch', 2, 8, 8):
    as_strided: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %as_strided : [num_users=1] = call_function[target=torch.as_strided](args = (%x, (2, 2, 8, 4), (128, 8, 16, 1)), kwargs = {})
    return as_strided
-- process.progress --
node 1/3 target=<built-in method as_strided of type object at 0x7fd5086f6ec0>
--
[GraphBuilder-JMU.make_tensor_input] x[1:batchx2x8x8]
[GraphBuilder-JMU] Message completed, there are 0 initializers, 0 nodes, 1 inputs, 1 outputs.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 2, 8, 8]
Constant(value_ints=[-1]) -> neg_1
Constant(value=[2, 2, 8, ...) -> val_0
Constant(value=[128, 8, 1...) -> val_1
Constant(value=[4]) -> rank_tensor
Constant(value_int=0) -> indices
SequenceEmpty() -> one_seq
Constant(value_int=4) -> rank_0
Loop(rank_0, , one_seq, indices, body=G1) -> one_seq_16, indices_17
Constant(value_ints=[-1]) -> tmp_18
  Reshape(x, tmp_18) -> self_flatten
Constant(value_int=0) -> storage_offset
  CastLike(storage_offset, indices_17) -> storage_offset_cast
  Add(indices_17, storage_offset_cast) -> indices_19
    Gather(self_flatten, indices_19) -> as_strided
output: name='as_strided' type=dtype('float32') shape=[2, 2, 8, 4]
----- subgraph ---- Loop - n6_2 - att.body=G1 -- level=1 -- i,cond_in,one_seq_1,indices_2 -> cond_out,one_seq_15,indices_13
input: name='i' type=dtype('int64') shape=None
input: name='cond_in' type=dtype('bool') shape=None
input: name='one_seq_1' type='NOTENSOR' shape=None
input: name='indices_2' type='NOTENSOR' shape=None
Constant(value_floats=[1.0]) -> tmp_14
  SequenceInsert(one_seq_1, tmp_14) -> one_seq_15
Constant(value=4) -> rank_3_cast
  Sub(rank_3_cast, i) -> tmp
Constant(value=1) -> int64_1_cast
  Sub(tmp, int64_1_cast) -> j
Reshape(j, neg_1) -> j_tensor
Gather(val_0, j_tensor, axis=0) -> size_dim_j
Slice(val_0, j_tensor, rank_tensor) -> size_after_j
  Expand(indices_2, size_after_j) -> indices_4
Gather(val_1, j_tensor, axis=0) -> stride_dim_j
Constant(value=0) -> int64_0_cast
Constant(value=1) -> int64_1_5_cast
  Range(int64_0_cast, size_dim_j, int64_1_5_cast) -> tmp_6
  Mul(tmp_6, stride_dim_j) -> add_value
Constant(value=0) -> int64_0_7_cast
  Equal(i, int64_0_7_cast) -> cond
    If(cond, then_branch=G2, else_branch=G3) -> shape_11
    Reshape(add_value, shape_11) -> add_value_12
    Add(indices_4, add_value_12) -> indices_13
Identity(cond_in) -> cond_out
output: name='cond_out' type=dtype('bool') shape=None
output: name='one_seq_15' type='NOTENSOR' shape=None
output: name='indices_13' type='NOTENSOR' shape=None
----- subgraph ---- If - n20 - att.then_branch=G2 -- level=2 --  -> shape
Identity(size_dim_j) -> shape
output: name='shape' type=dtype('int64') shape=[1]
----- subgraph ---- If - n20 - att.else_branch=G3 -- level=2 --  -> shape_10
Cast(size_dim_j, to=1) -> tmp_8
ConcatFromSequence(one_seq_1, axis=0) -> ones
  Concat(tmp_8, ones, axis=0) -> shape_9
    Cast(shape_9, to=7) -> shape_10
output: name='shape_10' type=dtype('int64') shape=None
----- subgraph ---- If - n20 - att.then_branch=G2 -- level=1 --  -> shape
Identity(size_dim_j) -> shape
output: name='shape' type=dtype('int64') shape=[1]
----- subgraph ---- If - n20 - att.else_branch=G3 -- level=1 --  -> shape_10
Cast(size_dim_j, to=1) -> tmp_8
ConcatFromSequence(one_seq_1, axis=0) -> ones
  Concat(tmp_8, ones, axis=0) -> shape_9
    Cast(shape_9, to=7) -> shape_10
output: name='shape_10' type=dtype('int64') shape=None

script

FAILED

number of input names provided (2) exceeded number of inputs (1)

AtenInterpolate

forward

def forward(self, x):
    y = torch.nn.functional.interpolate(
        x,
        scale_factor=2.0,
        mode="bilinear",
        recompute_scale_factor=False,
    )
    return y

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 2, 3, 4]
init: name='init7_s2_6_8' type=int64 shape=(2,) -- array([6, 8])      -- _aten_upsample_output_size.rsize
Shape(x, end=2, start=0) -> _shape_x0
  Concat(_shape_x0, init7_s2_6_8, axis=0) -> _onx_concat__shape_x00
Resize(x, , , _onx_concat__shape_x00, coordinate_transformation_mode=b'pytorch_half_pixel', mode=b'linear', nearest_mode=b'floor') -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 2, 6, 8]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 2, 3, 4]
init: name='init7_s2_6_8' type=int64 shape=(2,) -- array([6, 8])      -- _aten_upsample_output_size.rsize
Shape(x, end=2, start=0) -> _shape_x0
  Concat(_shape_x0, init7_s2_6_8, axis=0) -> _onx_concat__shape_x00
Resize(x, , , _onx_concat__shape_x00, coordinate_transformation_mode=b'pytorch_half_pixel', mode=b'linear', nearest_mode=b'floor') -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 2, 6, 8]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 2, 3, 4]
init: name='init7_s2_6_8' type=int64 shape=(2,) -- array([6, 8])      -- _aten_upsample_output_size.rsize
Shape(x, end=2, start=0) -> _shape_x0
  Concat(_shape_x0, init7_s2_6_8, axis=0) -> _onx_concat__shape_x00
Resize(x, , , _onx_concat__shape_x00, coordinate_transformation_mode=b'pytorch_half_pixel', mode=b'linear', nearest_mode=b'floor') -> output
output: name='output' type=dtype('float32') shape=['d_output_0', 'd_output_1', 'd_output_2', 'd_output_3']

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 2, 3, 4]
Constant(value_floats=[1.0,1.0,2.0,2.0]) -> val_0
Resize(x, , val_0, keep_aspect_ratio_policy=b'stretch', antialias=0, extrapolation_value=0.00, exclude_outside=0, nearest_mode=b'floor', coordinate_transformation_mode=b'pytorch_half_pixel', cubic_coeff_a=-0.75, mode=b'linear') -> upsample_bilinear2d
output: name='upsample_bilinear2d' type=dtype('float32') shape=['s0', 2, 6, 8]

script

FAILED

number of input names provided (2) exceeded number of inputs (1)

AtenNonZero

forward

def forward(self, x):
    y = torch.nonzero(x)
    return y

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
NonZero(x) -> _onx_nonzero_x0
  Transpose(_onx_nonzero_x0, perm=[1,0]) -> output_0
output: name='output_0' type=dtype('int64') shape=['NEWDIM_nonzero', 2]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
NonZero(x) -> _onx_nonzero_x0
  Transpose(_onx_nonzero_x0, perm=[1,0]) -> output_0
output: name='output_0' type=dtype('int64') shape=['NEWDIM_nonzero', 2]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
NonZero(x) -> _onx_nonzero_x0
  Transpose(_onx_nonzero_x0, perm=[1,0]) -> output
output: name='output' type=dtype('int64') shape=['NEWDIM_nonzero', 2]

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='pkg.onnxscript.torch_lib' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
NonZero(x) -> tmp
  Transpose(tmp, perm=[1,0]) -> nonzero
output: name='nonzero' type=dtype('int64') shape=['u0', 2]

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

AtenNonZeroTuple

forward

def forward(self, x):
    y = torch.nonzero(x, as_tuple=True)
    return y[0], y[1]

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
NonZero(x) -> _onx_nonzero_x0
  Split(_onx_nonzero_x0, num_outputs=2) -> _onx_split_nonzero_x00, _onx_split_nonzero_x01
    Reshape(_onx_split_nonzero_x00, init7_s1_-1) -> output_0
Reshape(_onx_split_nonzero_x01, init7_s1_-1) -> output_1
output: name='output_0' type=dtype('int64') shape=['u1']
output: name='output_1' type=dtype('int64') shape=['u1']

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
NonZero(x) -> _onx_nonzero_x0
  Split(_onx_nonzero_x0, num_outputs=2) -> _onx_split_nonzero_x00, _onx_split_nonzero_x01
    Reshape(_onx_split_nonzero_x00, init7_s1_-1) -> output_0
Reshape(_onx_split_nonzero_x01, init7_s1_-1) -> output_1
output: name='output_0' type=dtype('int64') shape=['u3']
output: name='output_1' type=dtype('int64') shape=['u3']

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
NonZero(x) -> _onx_nonzero_x0
  Split(_onx_nonzero_x0, num_outputs=2) -> _onx_split_nonzero_x00, _onx_split_nonzero_x01
    Reshape(_onx_split_nonzero_x00, init7_s1_-1) -> output_0
Reshape(_onx_split_nonzero_x01, init7_s1_-1) -> output_1
output: name='output_0' type=dtype('int64') shape=['d_output_0_0']
output: name='output_1' type=dtype('int64') shape=['d_output_1_0']

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='pkg.onnxscript.torch_lib' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
Constant(value_ints=[1]) -> unbind_axis
NonZero(x) -> tmp
  Transpose(tmp, perm=[1,0]) -> nonzero
    Split(nonzero, axis=1, num_outputs=2) -> unbind_split_0, unbind_split_1
  Squeeze(unbind_split_0, unbind_axis) -> unbind_split_0_squeeze
    Identity(unbind_split_0_squeeze) -> getitem
  Squeeze(unbind_split_1, unbind_axis) -> unbind_split_1_squeeze
    Identity(unbind_split_1_squeeze) -> getitem_1
output: name='getitem' type=dtype('int64') shape=['u0']
output: name='getitem_1' type=dtype('int64') shape=['u0']

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

AtenRollPos

forward

def forward(self, x):
    return torch.roll(x, 1, -1)

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_-1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_-1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3, 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_-1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_-1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3, 4]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_-1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_-1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> output
output: name='output' type=dtype('float32') shape=['batch', 3, 4]

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 3, 4]
Constant(value_ints=[-1]) -> neg_1
Constant(value=[-1]) -> dim_tensor
Constant(value=[1]) -> shift_tensor
Constant(value=[3]) -> slice_length_3
Constant(value_ints=[0]) -> tmp_4
  Slice(x, tmp_4, slice_length_3, dim_tensor) -> suffix
Size(x) -> tmp_5
  Reshape(tmp_5, neg_1) -> tmp_6
  Slice(x, slice_length_3, tmp_6, dim_tensor) -> prefix
    Concat(prefix, suffix, axis=-1) -> roll
output: name='roll' type=dtype('float32') shape=['s0', 3, 4]

script

FAILED

number of input names provided (2) exceeded number of inputs (1)

AtenRollRelu

forward

def forward(self, x):
    return torch.relu(torch.roll(x, -1, -1))

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> _onx_concat_slice_x00
    Relu(_onx_concat_slice_x00) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3, 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> _onx_concat_slice_x00
    Relu(_onx_concat_slice_x00) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3, 4]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 4]
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape
init: name='init7_s1_-1' type=int64 shape=(1,) -- array([-1])         -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape
Slice(x, init7_s1_1, init7_s1_4, init7_s1_-1) -> _onx_slice_x0
Slice(x, init7_s1_0, init7_s1_1, init7_s1_-1) -> _onx_slice_x02
  Concat(_onx_slice_x0, _onx_slice_x02, axis=-1) -> _onx_concat_slice_x00
    Relu(_onx_concat_slice_x00) -> output
output: name='output' type=dtype('float32') shape=['batch', 3, 4]

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 3, 4]
Constant(value_ints=[-1]) -> neg_1
Constant(value=[-1]) -> dim_tensor
Constant(value=[-1]) -> shift_tensor
Constant(value=[1]) -> slice_length_3
Constant(value_ints=[0]) -> tmp_4
  Slice(x, tmp_4, slice_length_3, dim_tensor) -> suffix
Size(x) -> tmp_5
  Reshape(tmp_5, neg_1) -> tmp_6
  Slice(x, slice_length_3, tmp_6, dim_tensor) -> prefix
    Concat(prefix, suffix, axis=-1) -> roll
      Relu(roll) -> relu
output: name='relu' type=dtype('float32') shape=['s0', 3, 4]

script

FAILED

number of input names provided (2) exceeded number of inputs (1)

BuildInIsInstance

forward

def forward(self, x, lx: list | torch.Tensor):
    if isinstance(lx, list):
        t = lx[0] * lx[1].sum(axis=1, keepdim=True)
        return torch.sigmoid(self.linear(x)) - self.buff + t
    return torch.sigmoid(self.linear(x)) - self.buff + lx

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.431,  0.023, -0.047], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.475], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub
    Add(sub, mul) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([0.192, 0.37 , 0.174], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.424], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul_1
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub_4
    Add(sub_4, mul_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

FAILED

Type is unknown for result 'lx', known_types={'x': 1, 'linear.weight': 1, 'linear.bias': 1, '_sub_Linear_input_1': 1, '_sub_Linear__onx_transpose_weight0': 1, '_sub_Linear__onx_matmul_input_10': 1, '_sub_Linear_linear': 1, '_sub_Linear_output': 1, 'linear': 1, 'sigmoid': 1, 'buff': 1, 'sub': 1}
--DEBUG--
[GraphBuilder-OSU] Message starts, there are 3 initializers, 8 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'},
           {'axis': 0, 'input_name': ('lx', 0)},
           {'axis': 0, 'input_name': ('lx', 1)}]}
dynamic_dimensions_source_flat=['x', ('lx', 0), ('lx', 1)]
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>},
        {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}],
 'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_sub_Linear__onx_matmul_input_10': 1,
 '_sub_Linear__onx_transpose_weight0': 1,
 '_sub_Linear_input_1': 1,
 '_sub_Linear_linear': 1,
 '_sub_Linear_output': 1,
 'buff': 1,
 'linear': 1,
 'linear.bias': 1,
 'linear.weight': 1,
 'sigmoid': 1,
 'sub': 1,
 'x': 1}
_known_shapes={'_sub_Linear__onx_matmul_input_10': ('batch', 1),
 '_sub_Linear__onx_transpose_weight0': (3, 1),
 '_sub_Linear_input_1': ('batch', 3),
 '_sub_Linear_linear': ('batch', 1),
 '_sub_Linear_output': ('batch', 1),
 'buff': (1,),
 'linear': ('batch', 1),
 'linear.bias': (1,),
 'linear.weight': (1, 3),
 'sigmoid': ('batch', 1),
 'sub': ('batch', 1),
 'x': ('batch', 3)}
_known_value_shape={}
_known_constants=['_sub_Linear__onx_transpose_weight0', 'buff', 'linear.bias', 'linear.weight']
_known_ranks={}
--TORCH-USERS--
    add -> {output}
    buff -> {sub}
    linear -> {sigmoid}
    lx -> {add}
    sigmoid -> {sub}
    sub -> {add}
    x -> {linear}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([4, 3])), '')) --- 1:2:('batch', 3):
    lx: ('run_node', ('', '')) --- :::
    linear: ('run_node', ('', '')) --- 1:2:('batch', 1):
    sigmoid: ('run_node', ('', '')) --- 1:2:('batch', 1):
    buff: ('run_node', ('', '')) --- 1:1:(1,):
    sub: ('run_node', ('', '')) --- 1:2:('batch', 1):
    add: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %lx : list | torch.Tensor [num_users=1] = placeholder[target=lx]
    %linear : [num_users=1] = call_module[target=linear](args = (%x,), kwargs = {})
    %sigmoid : [num_users=1] = call_function[target=torch.sigmoid](args = (%linear,), kwargs = {})
    %buff : [num_users=1] = get_attr[target=buff]
    %sub : [num_users=1] = call_function[target=operator.sub](args = (%sigmoid, %buff), kwargs = {})
    %add : [num_users=1] = call_function[target=operator.add](args = (%sub, %lx), kwargs = {})
    return add
-- process.progress --
node 6/8 target=<built-in function add>
--
[GraphBuilder-OSU.make_tensor_input] x[1:batchx3]
[GraphBuilder-OSU.make_tensor_input] lx[0:]
[GraphBuilder-OSU.make_initializer] linear.weight[torch.float32:torch.float32:[-0.369383841753006, 0.3992883265018463, -0.3257561922073364]] - SOURCE: GraphBuilder.make_nodes/fromlinear.weight##DynamoInterpret.get_attr.1/P(linear.weight)
[GraphBuilder-OSU.make_initializer] linear.bias[torch.float32:torch.float32:[-0.14722837507724762]] - SOURCE: GraphBuilder.make_nodes/fromlinear.bias##DynamoInterpret.get_attr.1/P(linear.bias)
[GraphBuilder-OSU.make_initializer] buff[torch.float32:torch.float32:[0.5]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-OSU.make_node] .make_nodes     [#:#   ] Identity:['x']->['_sub_Linear_input_1']
[GraphBuilder-OSU.make_node] linear          [#:#   ] Transpose:['linear.weight']->['_sub_Linear__onx_transpose_weight0']
[GraphBuilder-OSU.make_node] Opset           [##:#  ] MatMul:['_sub_Linear_input_1', '_sub_Linear__onx_transpose_weight0']->['_sub_Linear__onx_matmul_input_10']
[GraphBuilder-OSU.make_node] Opset2          [##:#  ] Add:['_sub_Linear__onx_matmul_input_10', 'linear.bias']->['_sub_Linear_linear']
[GraphBuilder-OSU.make_node] .output         [#:#   ] Identity:['_sub_Linear_linear']->['_sub_Linear_output']
[GraphBuilder-OSU.make_node] .make_nodes2    [#:#   ] Identity:['_sub_Linear_output']->['linear']
[GraphBuilder-OSU.make_node] sigmoid         [#:#   ] Sigmoid:['linear']->['sigmoid']
[GraphBuilder-OSU.make_node] sub             [##:#  ] Sub:['sigmoid', 'buff']->['sub']
[GraphBuilder-OSU] Message completed, there are 3 initializers, 8 nodes, 2 inputs, 2 outputs..

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3]
input: name='lx_0' type=dtype('float32') shape=['s0', 1]
input: name='lx_1' type=dtype('float32') shape=['s0', 2]
init: name='linear.weight' type=float32 shape=(1, 3) -- array([0.062, 0.492, 0.576], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.56], dtype=float32)
init: name='buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)
Constant(value=[1]) -> val_3
  ReduceSum(lx_1, val_3, noop_with_empty_axes=0, keepdims=1) -> sum_1
    Mul(lx_0, sum_1) -> mul_1
Gemm(x, linear.weight, linear.bias, beta=1.00, transB=1, alpha=1.00, transA=0) -> linear
  Sigmoid(linear) -> sigmoid
    Sub(sigmoid, buff) -> sub_4
      Add(sub_4, mul_1) -> add_15
output: name='add_15' type=dtype('float32') shape=['s0', 1]

script

FAILED

unable to convert dynamic shapes {'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, 'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}

BuildInLen

forward

def forward(self, x, lx: list):
    t = lx[0] * lx[1].sum(axis=1, keepdim=True)
    if len(lx) > 2:
        t = t + lx[2].sum(axis=1, keepdim=True)
    return torch.sigmoid(self.linear(x)) - self.buff + t

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.355,  0.159, -0.052], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.511], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub
    Add(sub, mul) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([ 0.304, -0.505, -0.106], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.286], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul_1
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub_4
    Add(sub_4, mul_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

FAILED

len(.) expects an integer, len needs to be replaced. You should use _len.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3]
input: name='lx_0' type=dtype('float32') shape=['s0', 1]
input: name='lx_1' type=dtype('float32') shape=['s0', 2]
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.152, -0.416,  0.442], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.312], dtype=float32)
init: name='buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)
Constant(value=[1]) -> val_3
  ReduceSum(lx_1, val_3, noop_with_empty_axes=0, keepdims=1) -> sum_1
    Mul(lx_0, sum_1) -> mul_1
Gemm(x, linear.weight, linear.bias, beta=1.00, transB=1, alpha=1.00, transA=0) -> linear
  Sigmoid(linear) -> sigmoid
    Sub(sigmoid, buff) -> sub_4
      Add(sub_4, mul_1) -> add_15
output: name='add_15' type=dtype('float32') shape=['s0', 1]

script

FAILED

unable to convert dynamic shapes {'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, 'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}

ComplexPolar

forward

def forward(self, x, angle):
    return torch.polar(x, angle)

custom-fallback

FAILED

[ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. Type Error: Type 'tensor(complex64)' of input parameter (_onx_cast_sin_angle00) of operator (Mul) in node (polar5) is invalid.

custom-dec

FAILED

[ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. Type Error: Type 'tensor(complex64)' of input parameter (_onx_cast_sin_angle00) of operator (Mul) in node (polar5) is invalid.

custom-tracing

FAILED

[ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. Type Error: Type 'tensor(complex64)' of input parameter (_onx_cast_sin_angle00) of operator (Mul) in node (polar5) is invalid.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='pkg.onnxscript.torch_lib' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
input: name='angle' type=dtype('float32') shape=['s0', 4]
Constant(value=[-1]) -> int64_m1_1d
Cos(angle) -> tmp
  Mul(x, tmp) -> tmp_0
  Unsqueeze(tmp_0, int64_m1_1d) -> real
Sin(angle) -> tmp_1
  Mul(x, tmp_1) -> tmp_2
Constant(value=[-1]) -> int64_m1_1d_3
  Unsqueeze(tmp_2, int64_m1_1d_3) -> imag
    Concat(real, imag, axis=-1) -> polar
output: name='polar' type=dtype('float32') shape=['s0', 4, 2]

script

FAILED

Exporting the operator 'aten::polar' to ONNX opset version 17 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues.

ControlFlowCond

forward

def forward(self, x):
    def true_fn(x):
        return torch.sin(x)

    def false_fn(x):
        return torch.cos(x)

    return torch.cond(x.sum() > 0, true_fn, false_fn, [x])

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Sin(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Cos(x) -> output_0
output: name='output_0' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Sin(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Cos(x) -> output_0
output: name='output_0' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

FAILED

no dynamic shape

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowCond2Inputs

forward

def forward(self, x, y):
    def true_fn(x, y):
        return torch.sin(x), torch.cos(x) + y

    def false_fn(x, y):
        return torch.cos(x), torch.sin(x) + y

    return torch.cond(x.sum() > 0, true_fn, false_fn, [x, y])

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0, output_1
output: name='output_0' type=dtype('float32') shape=['batch', 3]
output: name='output_1' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0,cond#1
false_graph_0[local_functions](x, y) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0,cond#1
true_graph_0[local_functions](x, y) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
input: 'y'
Cos(x) -> cos
  Add(cos, y) -> output_1
Sin(x) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
input: 'y'
Cos(x) -> output_0
Sin(x) -> sin
  Add(sin, y) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0, output_1
output: name='output_0' type=dtype('float32') shape=['batch', 3]
output: name='output_1' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0,cond#1
false_graph_0[local_functions](x, y) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0,cond#1
true_graph_0[local_functions](x, y) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
input: 'y'
Cos(x) -> cos
  Add(cos, y) -> output_1
Sin(x) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
input: 'y'
Cos(x) -> output_0
Sin(x) -> sin
  Add(sin, y) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

FAILED

no dynamic shape

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowCond2Outputs

forward

def forward(self, x):
    def true_fn(x):
        return torch.sin(x), torch.cos(x)

    def false_fn(x):
        return torch.cos(x), torch.sin(x)

    return torch.cond(x.sum() > 0, true_fn, false_fn, [x])

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0, output_1
output: name='output_0' type=dtype('float32') shape=['batch', 3]
output: name='output_1' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0,cond#1
false_graph_0[local_functions](x) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0,cond#1
true_graph_0[local_functions](x) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Cos(x) -> output_1
Sin(x) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Cos(x) -> output_0
Sin(x) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0, output_1
output: name='output_0' type=dtype('float32') shape=['batch', 3]
output: name='output_1' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0,cond#1
false_graph_0[local_functions](x) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0,cond#1
true_graph_0[local_functions](x) -> cond#0, cond#1
output: name='cond#0' type='NOTENSOR' shape=None
output: name='cond#1' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Cos(x) -> output_1
Sin(x) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Cos(x) -> output_0
Sin(x) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

FAILED

no dynamic shape

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowCondConstant

forward

def forward(self, x):
    def true_fn(x):
        return torch.sin(x) - torch.ones(x.shape, dtype=x.dtype)

    def false_fn(x):
        return torch.cos(x) + torch.ones((1, 1024), dtype=x.dtype)

    return torch.cond(x.sum() > 0, true_fn, false_fn, [x])

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 1024]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1024]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Constant(value=[1024]) -> init7_s1_1024
Sin(x) -> sin
Shape(x, end=1, start=0) -> _shape_x0
  Concat(_shape_x0, init7_s1_1024, axis=0) -> _onx_concat_unsqueeze_sym_size_int00
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int00, value=[1.0]) -> ones
  Sub(sin, ones) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Constant(value=[1, 1024]) -> init7_s2_1_1024
  ConstantOfShape(init7_s2_1_1024, value=[1.0]) -> ones
Cos(x) -> cos
  Add(cos, ones) -> output_0
output: name='output_0' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 1024]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1024]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Constant(value=[1024]) -> init7_s1_1024
Shape(x, end=1, start=0) -> _shape_x0
  Concat(_shape_x0, init7_s1_1024, axis=0) -> _onx_concat_unsqueeze_sym_size_int00
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int00, value=[1.0]) -> ones
Sin(x) -> sin
  Sub(sin, ones) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions' version=1
input: 'x'
Constant(value=[1, 1024]) -> init7_s2_1_1024
  ConstantOfShape(init7_s2_1_1024, value=[1.0]) -> ones
Cos(x) -> cos
  Add(cos, ones) -> output_0
output: name='output_0' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.torch.__subgraph__' version=1
input: name='x' type=dtype('float32') shape=['s0', 1024]
Constant(value=0.0) -> scalar_tensor_default
ReduceSum(x, noop_with_empty_axes=0, keepdims=0) -> sum_1
  Greater(sum_1, scalar_tensor_default) -> gt
    If(gt, then_branch=G1, else_branch=G2) -> getitem
output: name='getitem' type=dtype('float32') shape=['s0', 1024]
----- subgraph ---- If - node_If_4 - att.then_branch=G1 -- level=1 --  -> sub_3_true_graph_0
Constant(value=[-1]) -> val_1
Shape(x, end=1, start=0) -> val_0_2
  Squeeze(val_0_2) -> sym_size_int
  Reshape(sym_size_int, val_1, allowzero=0) -> val_2
Sin(x) -> sin
Constant(value=[1024]) -> val_3
  Concat(val_2, val_3, axis=0) -> val_4
Constant(value=1.0) -> val_7
  Expand(val_7, val_4) -> ones
  Sub(sin, ones) -> sub_3_true_graph_0
output: name='sub_3_true_graph_0' type=dtype('float32') shape=['', 1024]
----- subgraph ---- If - node_If_4 - att.else_branch=G2 -- level=1 --  -> add_6_false_graph_0
Constant(value=[[1.0, 1.0...) -> ones_2
Cos(x) -> cos
  Add(cos, ones_2) -> add_6_false_graph_0
output: name='add_6_false_graph_0' type=dtype('float32') shape=['s0', 1024]

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowCondNestedModule

forward

def forward(self, x):
    def true_fn(x):
        return self.submodule(x)

    def false_fn(x):
        return x - self.weight

    y = torch.cond(x.sum() > 0, true_fn, false_fn, [x])
    return y

custom-fallback

opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: name='x' type=dtype('int64') shape=['batch']
init: name='init7_s_0' type=int64 shape=() -- array([0])              -- shape_type_compute._cast_inputs.1(gt_Scalar)
init: name='submodule.weight' type=float32 shape=(1,) -- array([100.], dtype=float32)-- DynamoInterpret.placeholder.1/P(submodule.weight)
init: name='weight' type=float32 shape=(1,) -- array([42.], dtype=float32)-- DynamoInterpret.placeholder.1/P(weight)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init7_s_0) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch']
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x, submodule.weight, weight) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x, submodule.weight, weight) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'p_submodule_weight'
input: 'x'
Cast(x, to=1) -> _onx_cast_x0
  Mul(_onx_cast_x0, p_submodule_weight) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'p_submodule_weight'
input: 'x'
Cast(x, to=1) -> _onx_cast_x0
  Div(_onx_cast_x0, p_submodule_weight) -> output_0
output: name='output_0' type=? shape=?
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
input: 'p_submodule_weight'
input: 'p_weight'
Abs(x) -> abs_1
  ReduceSum(abs_1, keepdims=0) -> sum_1
Constant(value=100) -> init7_s_100
  Greater(sum_1, init7_s_100) -> gt
    If(gt, else_branch=G3, then_branch=G4) -> output_0
output: name='output_0' type=? shape=?
----- subgraph ---- If - cond - att.else_branch=G3 -- level=1 --  -> cond#0
false_graph_0[local_functions.0](p_submodule_weight, x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G4 -- level=1 --  -> cond#0
true_graph_0[local_functions.0](p_submodule_weight, x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: 'x'
input: 'p_submodule_weight'
input: 'p_weight'
Cast(x, to=1) -> _onx_cast_x0
  Sub(_onx_cast_x0, p_weight) -> output_0
output: name='output_0' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: name='x' type=dtype('int64') shape=['batch']
init: name='init7_s_0' type=int64 shape=() -- array([0])              -- shape_type_compute._cast_inputs.1(gt_Scalar)
init: name='weight' type=float32 shape=(1,) -- array([42.], dtype=float32)-- DynamoInterpret.placeholder.1/P(weight)
init: name='submodule.weight' type=float32 shape=(1,) -- array([100.], dtype=float32)-- DynamoInterpret.placeholder.1/P(submodule.weight)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init7_s_0) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch']
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x, submodule.weight, weight) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x, submodule.weight, weight) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'p_submodule_weight'
input: 'x'
Cast(x, to=1) -> _onx_cast_x0
  Mul(_onx_cast_x0, p_submodule_weight) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'p_submodule_weight'
input: 'x'
Cast(x, to=1) -> _onx_cast_x0
  Div(_onx_cast_x0, p_submodule_weight) -> output_0
output: name='output_0' type=? shape=?
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
input: 'p_submodule_weight'
input: 'p_weight'
Abs(x) -> abs_1
  ReduceSum(abs_1, keepdims=0) -> sum_1
Constant(value=100) -> init7_s_100
  Greater(sum_1, init7_s_100) -> gt
    If(gt, else_branch=G3, then_branch=G4) -> output_0
output: name='output_0' type=? shape=?
----- subgraph ---- If - cond - att.else_branch=G3 -- level=1 --  -> cond#0
false_graph_0[local_functions.0](p_submodule_weight, x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G4 -- level=1 --  -> cond#0
true_graph_0[local_functions.0](p_submodule_weight, x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: 'x'
input: 'p_submodule_weight'
input: 'p_weight'
Cast(x, to=1) -> _onx_cast_x0
  Sub(_onx_cast_x0, p_weight) -> output_0
output: name='output_0' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.torch.__subgraph__' version=1
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('int64') shape=['s0']
init: name='weight' type=float32 shape=(1,) -- array([42.], dtype=float32)
init: name='submodule.weight' type=float32 shape=(1,) -- array([100.], dtype=float32)
Constant(value=0) -> val_0
ReduceSum(x, noop_with_empty_axes=0, keepdims=0) -> sum_1
  Greater(sum_1, val_0) -> gt
    If(gt, then_branch=G1, else_branch=G2) -> getitem
output: name='getitem' type=dtype('float32') shape=['s0']
----- subgraph ---- If - node_If_3 - att.then_branch=G1 -- level=1 --  -> getitem_true_graph_0
Abs(x) -> abs_1
  ReduceSum(abs_1, noop_with_empty_axes=0, keepdims=0) -> sum_1_2
Constant(value=100) -> val_0_2
  Greater(sum_1_2, val_0_2) -> gt_2
    If(gt_2, then_branch=G3, else_branch=G4) -> getitem_true_graph_0
output: name='getitem_true_graph_0' type='NOTENSOR' shape=None
----- subgraph ---- If - node_If_4 - att.then_branch=G3 -- level=2 --  -> mul_1_true_graph_0__true_graph_0
Cast(x, to=1) -> convert_element_type_default
Mul(convert_element_type_default, submodule.weight) -> mul_1_true_graph_0__true_graph_0
output: name='mul_1_true_graph_0__true_graph_0' type=dtype('float32') shape=['s0']
----- subgraph ---- If - node_If_4 - att.else_branch=G4 -- level=2 --  -> div_true_graph_0__false_graph_0
Cast(x, to=1) -> convert_element_type_default_2
Div(convert_element_type_default_2, submodule.weight) -> div_true_graph_0__false_graph_0
output: name='div_true_graph_0__false_graph_0' type=dtype('float32') shape=['s0']
----- subgraph ---- If - node_If_4 - att.then_branch=G3 -- level=1 --  -> mul_1_true_graph_0__true_graph_0
Cast(x, to=1) -> convert_element_type_default
Mul(convert_element_type_default, submodule.weight) -> mul_1_true_graph_0__true_graph_0
output: name='mul_1_true_graph_0__true_graph_0' type=dtype('float32') shape=['s0']
----- subgraph ---- If - node_If_4 - att.else_branch=G4 -- level=1 --  -> div_true_graph_0__false_graph_0
Cast(x, to=1) -> convert_element_type_default_2
Div(convert_element_type_default_2, submodule.weight) -> div_true_graph_0__false_graph_0
output: name='div_true_graph_0__false_graph_0' type=dtype('float32') shape=['s0']
----- subgraph ---- If - node_If_3 - att.else_branch=G2 -- level=1 --  -> sub_1_false_graph_0
Cast(x, to=1) -> convert_element_type_default_3
Sub(convert_element_type_default_3, weight) -> sub_1_false_graph_0
output: name='sub_1_false_graph_0' type=dtype('float32') shape=['s0']

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowCondNonZero

forward

def forward(self, input_ids, image_features, vocab_size):
    def then_branch(input_ids, image_features, vocab_size):
        input_shape = input_ids.size()
        input_ids = input_ids.view(-1, input_shape[-1])

        condition = (input_ids < 0) & (input_ids > -int(1e9))
        positions = torch.nonzero(condition, as_tuple=True)
        input_ids = input_ids.clamp_min(0).clamp_max(vocab_size)
        return (input_ids, positions[0], positions[1])

    def else_branch(input_ids, image_features, vocab_size):
        r = torch.where(torch.zeros((1, 1), dtype=torch.bool))
        return (input_ids, r[0], r[1])

    a, b, c = torch.cond(
        image_features.numel() > 0,
        then_branch,
        else_branch,
        [input_ids, image_features, vocab_size],
    )
    return a, b, c

custom-fallback

FAILED

None of the following options [ExportOptions(), ExportOptions(strict=False), ExportOptions(decomposition_table='default'), ExportOptions(strict=False, decomposition_table='default'), ExportOptions(dynamo=True), ExportOptions(decomposition_table='default', dynamo=True), ExportOptions(jit=True)] worked, args=(T7r2,T1r2,int), kwargs=None, exception=
-----
[(ExportOptions(),
  UncapturedHigherOrderOpError('Expected true_fn_output and false_fn_output to have same metadata but found:\npair[1] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\npair[2] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 339, in forward\n    a, b, c = torch.cond(\n  File "/home/xadupre/vv/this312/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 138, in cond\n    return cond_op(pred, true_fn, false_fn, operands)\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(strict=False),
  RuntimeError('Expect operands to be a tuple of possibly nested dict/list/tuple that only consists of tensor leaves, but got [FakeTensor(..., size=(s1, 12), dtype=torch.int64), FakeTensor(..., size=(s2, s3)), 1025].')),
 (ExportOptions(decomposition_table='default'),
  UncapturedHigherOrderOpError('Expected true_fn_output and false_fn_output to have same metadata but found:\npair[1] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\npair[2] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 339, in forward\n    a, b, c = torch.cond(\n  File "/home/xadupre/vv/this312/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 138, in cond\n    return cond_op(pred, true_fn, false_fn, operands)\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(strict=False, decomposition_table='default'),
  RuntimeError('Expect operands to be a tuple of possibly nested dict/list/tuple that only consists of tensor leaves, but got [FakeTensor(..., size=(s1, 12), dtype=torch.int64), FakeTensor(..., size=(s2, s3)), 1025].')),
 (ExportOptions(dynamo=True),
  UncapturedHigherOrderOpError('Expected true_fn_output and false_fn_output to have same metadata but found:\npair[1] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\npair[2] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 339, in forward\n    a, b, c = torch.cond(\n  File "/home/xadupre/vv/this312/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 138, in cond\n    return cond_op(pred, true_fn, false_fn, operands)\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(decomposition_table='default', dynamo=True),
  UncapturedHigherOrderOpError('Expected true_fn_output and false_fn_output to have same metadata but found:\npair[1] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\npair[2] differ in \'shape: torch.Size([u0]) vs torch.Size([u1])\', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 339, in forward\n    a, b, c = torch.cond(\n  File "/home/xadupre/vv/this312/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 138, in cond\n    return cond_op(pred, true_fn, false_fn, operands)\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(jit=True),
  RuntimeError("Type 'Tuple[Tensor, Tensor, int]' cannot be traced. Only Tensors and (possibly nested) Lists, Dicts, and Tuples of Tensors can be traced"))]

custom-dec

FAILED

Expected true_fn_output and false_fn_output to have same metadata but found:
pair[1] differ in 'shape: torch.Size([u0]) vs torch.Size([u1])', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)
pair[2] differ in 'shape: torch.Size([u0]) vs torch.Size([u1])', where lhs is FakeTensor(..., size=(u0,), dtype=torch.int64) and rhs is FakeTensor(..., size=(u1,), dtype=torch.int64)

from user code:
   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 339, in forward
    a, b, c = torch.cond(
  File "/home/xadupre/vv/this312/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 138, in cond
    return cond_op(pred, true_fn, false_fn, operands)

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

custom-tracing

FAILED

val is None for node=output, output=(getitem, getitem_1, getitem_2), a='getitem', o='output_0', has_type=False, has_rank=False, has_shape=False, 
meta={}
node.__dict__={'graph': <torch.fx.graph.Graph object at 0x7fd2da06f950>, 'name': 'output', 'op': 'output', 'target': 'output', '_input_nodes': {getitem: None, getitem_1: None, getitem_2: None}, '_args': ((getitem, getitem_1, getitem_2),), '_kwargs': {}, 'users': {}, 'type': None, '_sort_key': (11,), '_repr_fn': None, 'meta': {}}
--DEBUG--
[GraphBuilder-UKE] Message starts, there are 2 initializers, 11 nodes, 3 inputs, 3 outputs.
--LOCAL FUNCTIONS--
    local_functions,_cb_cond_then_branch_0(['x', 'y', 'z']) -> ['output_0', 'output_1', 'output_2']
    local_functions,_cb_cond_else_branch_0(['x', 'y', 'z']) -> ['output_0', 'output_1', 'output_2']
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
   seq_length = WrapSym(seq_length)
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
   'seq_length' = <class 'list'>
     tuple
       'seq_length'
       ERR**: <class 'torch.SymInt'>:'seq_length'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'input_ids'},
           {'axis': 0, 'input_name': 'image_features'}],
 'seq_length': [{'axis': 1, 'input_name': 'image_features'}]}
dynamic_dimensions_source_flat=[0, 1]
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes=({0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>},
 {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>,
  1: <class 'experimental_experiment.torch_interpreter.eval.model_cases.seq_length'>},
 None)
_known_types={'_reshape_init7_s_00': 7,
 '_reshape_numel0': 7,
 'gt': 9,
 'image_features': 1,
 'init7_s1_1': 7,
 'init7_s_0': 7,
 'input_ids': 7,
 'numel': 7,
 'vocab_size': 7}
_known_shapes={'_reshape_init7_s_00': (1,),
 '_reshape_numel0': (1,),
 'gt': (),
 'image_features': ('batch', 'seq_length'),
 'init7_s1_1': (1,),
 'init7_s_0': (),
 'input_ids': ('batch', 12),
 'numel': (),
 'vocab_size': ()}
_known_value_shape={}
_known_constants=['_reshape_init7_s_00', 'init7_s1_1', 'init7_s_0']
_known_ranks={}
--TORCH-USERS--
    _cb_cond_else_branch_0 -> {condcc}
    _cb_cond_then_branch_0 -> {condcc}
    condcc -> {getitem_1, getitem_2, getitem}
    getitem -> {output}
    getitem_1 -> {output}
    getitem_2 -> {output}
    gt -> {condcc}
    image_features -> {numel, condcc}
    input_ids -> {condcc}
    numel -> {gt}
    output -> set()
    vocab_size -> {condcc}
--TORCH-SHAPES--
    input_ids: ('run_node', (('example_value', torch.int64, torch.Size([2, 12])), '')) --- 7:2:('batch', 12):
    image_features: ('run_node', (('example_value', torch.float32, torch.Size([2, 16])), '')) --- 1:2:('batch', 'seq_length'):
    vocab_size: ('run_node', (('example_value', torch.int64, torch.Size([])), '')) --- 7:0:():
    numel: ('run_node', ('', '')) --- 7:0:():
    gt: ('run_node', ('', '')) --- 9:0:():
    _cb_cond_then_branch_0: ('run_node', ('', '')) --- :::
    _cb_cond_else_branch_0: ('run_node', ('', '')) --- :::
    condcc: ('run_node', ('', '')) --- :::
    getitem: ('run_node', ('', '')) --- :::
    getitem_1: ('run_node', ('', '')) --- :::
    getitem_2: ('run_node', ('', '')) --- :::
    output: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %input_ids : [num_users=1] = placeholder[target=input_ids]
    %image_features : [num_users=2] = placeholder[target=image_features]
    %vocab_size : [num_users=1] = placeholder[target=vocab_size]
    %numel : [num_users=1] = call_method[target=numel](args = (%image_features,), kwargs = {})
    %gt : [num_users=1] = call_function[target=operator.gt](args = (%numel, 0), kwargs = {})
    %_cb_cond_then_branch_0 : [num_users=1] = get_attr[target=_cb_cond_then_branch_0]
    %_cb_cond_else_branch_0 : [num_users=1] = get_attr[target=_cb_cond_else_branch_0]
    %condcc : [num_users=3] = call_function[target=torch.ops.higher_order.cond](args = (%gt, %_cb_cond_then_branch_0, %_cb_cond_else_branch_0, [%input_ids, %image_features, %vocab_size]), kwargs = {})
    %getitem : [num_users=1] = call_function[target=operator.getitem](args = (%condcc, 0), kwargs = {})
    %getitem_1 : [num_users=1] = call_function[target=operator.getitem](args = (%condcc, 1), kwargs = {})
    %getitem_2 : [num_users=1] = call_function[target=operator.getitem](args = (%condcc, 2), kwargs = {})
    return (getitem, getitem_1, getitem_2)
-- process.progress --
node 11/12 target=output
--
[GraphBuilder-UKE.make_tensor_input] input_ids[7:batchx12]
[GraphBuilder-UKE.make_tensor_input] image_features[1:batchxseq_length]
[GraphBuilder-UKE.make_tensor_input] vocab_size[7:]
[GraphBuilder-UKE.make_initializer] init7_s_0[int64:int64:[0]] - SOURCE: shape_type_compute._cast_inputs.1(gt)
[GraphBuilder-UKE.make_initializer] init7_s1_1[int64:int64:[1]] - SOURCE: Opset.make_node.1/Shape##Opset.make_node.1/Shape
[GraphBuilder-UKE.make_node] meth_numel      [#:#   ] Size:['image_features']->['numel']
[GraphBuilder-UKE.make_node] gt              [##:#  ] Reshape:['numel', 'init7_s1_1']->['_reshape_numel0']
[GraphBuilder-UKE.make_node] gt2             [##:#  ] Reshape:['init7_s_0', 'init7_s1_1']->['_reshape_init7_s_00']
[GraphBuilder-UKE.make_node] gt3             [##:#  ] Greater:['numel', 'init7_s_0']->['gt']
[GraphBuilder-UKE.make_node] cond            [#:--- ] If:['gt']->['condcc#0', 'condcc#1', 'condcc#2']
[GraphBuilder-UKE.make_node] getitemB_tuple  [-:-   ] Identity:['condcc#0']->['getitem']
[GraphBuilder-UKE.make_node] getitemB_tuple2 [-:-   ] Identity:['condcc#1']->['getitem_1']
[GraphBuilder-UKE.make_node] getitemB_tuple3 [-:-   ] Identity:['condcc#2']->['getitem_2']
[GraphBuilder-UKE.make_node] .output         [-:-   ] Identity:['getitem']->['output_0']
[GraphBuilder-UKE.make_node] .output2        [-:-   ] Identity:['getitem_1']->['output_1']
[GraphBuilder-UKE.make_node] .output3        [-:-   ] Identity:['getitem_2']->['output_2']
[GraphBuilder-UKE] Message completed, there are 2 initializers, 11 nodes, 3 inputs, 3 outputs.

dynamo-ir

FAILED

Failed to export the model with torch.export. This is step 1/3 of exporting the model to ONNX. Next steps:
- Modify the model code for `torch.export.export` to succeed. Refer to https://pytorch.org/docs/stable/generated/exportdb/index.html for more information.
- Debug `torch.export.export` and summit a PR to PyTorch.
- Create an issue in the PyTorch GitHub repository against the *torch.export* component and attach the full error stack as well as reproduction scripts.

## Exception summary

<class 'RuntimeError'>: Expect operands to be a tuple of possibly nested dict/list/tuple that only consists of tensor leaves, but got [FakeTensor(..., size=(s1, 12), dtype=torch.int64), FakeTensor(..., size=(s2, s3)), 1025].

(Refer to the full stack trace above for more information.)

script

FAILED

unable to convert dynamic shapes ({0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>, 1: <class 'experimental_experiment.torch_interpreter.eval.model_cases.seq_length'>}, None)

ControlFlowNestCond

forward

def forward(self, x):
    def true_fn2(x):
        def true_fn1(x):
            return torch.sin(x)

        def false_fn1(x):
            return torch.cos(x)

        return torch.cond(x.sum() < 0, true_fn1, false_fn1, [x])

    def false_fn2(x):
        return -x

    return torch.cond(x.sum() > 0, true_fn2, false_fn2, [x])

custom-fallback

opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Sin(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
Cos(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
Constant(value=0.0) -> init1_s_
ReduceSum(x, keepdims=0) -> sum_1
  Less(sum_1, init1_s_) -> lt
    If(lt, else_branch=G3, then_branch=G4) -> output_0
output: name='output_0' type=? shape=?
----- subgraph ---- If - cond - att.else_branch=G3 -- level=1 --  -> cond#0
false_graph_0[local_functions.0](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G4 -- level=1 --  -> cond#0
true_graph_0[local_functions.0](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: 'x'
Neg(x) -> output_0
output: name='output_0' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init1_s_' type=float32 shape=() -- array([0.], dtype=float32)-- shape_type_compute._cast_inputs.1(gt_Scalar)
ReduceSum(x, keepdims=0) -> sum_1
  Greater(sum_1, init1_s_) -> gt
    If(gt, else_branch=G1, then_branch=G2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3]
----- subgraph ---- If - cond - att.else_branch=G1 -- level=1 --  -> cond#0
false_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G2 -- level=1 --  -> cond#0
true_graph_0[local_functions](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=true_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'x'
Sin(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=false_graph_0 domain=local_functions.0
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
Cos(x) -> output_0
output: name='output_0' type=? shape=?
----- function name=true_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
input: 'x'
Constant(value=0.0) -> init1_s_
ReduceSum(x, keepdims=0) -> sum_1
  Less(sum_1, init1_s_) -> lt
    If(lt, else_branch=G3, then_branch=G4) -> output_0
output: name='output_0' type=? shape=?
----- subgraph ---- If - cond - att.else_branch=G3 -- level=1 --  -> cond#0
false_graph_0[local_functions.0](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- subgraph ---- If - cond - att.then_branch=G4 -- level=1 --  -> cond#0
true_graph_0[local_functions.0](x) -> cond#0
output: name='cond#0' type='NOTENSOR' shape=None
----- function name=false_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
opset: domain='local_functions.0' version=1
opset: domain='local_functions' version=1
input: 'x'
Neg(x) -> output_0
output: name='output_0' type=? shape=?

custom-tracing

FAILED

aten_meth_sum() missing 1 required positional argument: 'axis'

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.torch.__subgraph__' version=1
input: name='x' type=dtype('float32') shape=['s0', 3]
Constant(value=0.0) -> scalar_tensor_default
ReduceSum(x, noop_with_empty_axes=0, keepdims=0) -> sum_1
  Greater(sum_1, scalar_tensor_default) -> gt
    If(gt, then_branch=G1, else_branch=G2) -> getitem
output: name='getitem' type=dtype('float32') shape=['s0', 3]
----- subgraph ---- If - node_If_4 - att.then_branch=G1 -- level=1 --  -> getitem_true_graph_0
Constant(value=0.0) -> scalar_tensor_default_2
ReduceSum(x, noop_with_empty_axes=0, keepdims=0) -> sum_1_2
  Less(sum_1_2, scalar_tensor_default_2) -> lt
    If(lt, then_branch=G3, else_branch=G4) -> getitem_true_graph_0
output: name='getitem_true_graph_0' type='NOTENSOR' shape=None
----- subgraph ---- If - node_If_4_2 - att.then_branch=G3 -- level=2 --  -> sin_true_graph_0__true_graph_0
Sin(x) -> sin_true_graph_0__true_graph_0
output: name='sin_true_graph_0__true_graph_0' type=dtype('float32') shape=['s0', 3]
----- subgraph ---- If - node_If_4_2 - att.else_branch=G4 -- level=2 --  -> cos_true_graph_0__false_graph_0
Cos(x) -> cos_true_graph_0__false_graph_0
output: name='cos_true_graph_0__false_graph_0' type=dtype('float32') shape=['s0', 3]
----- subgraph ---- If - node_If_4_2 - att.then_branch=G3 -- level=1 --  -> sin_true_graph_0__true_graph_0
Sin(x) -> sin_true_graph_0__true_graph_0
output: name='sin_true_graph_0__true_graph_0' type=dtype('float32') shape=['s0', 3]
----- subgraph ---- If - node_If_4_2 - att.else_branch=G4 -- level=1 --  -> cos_true_graph_0__false_graph_0
Cos(x) -> cos_true_graph_0__false_graph_0
output: name='cos_true_graph_0__false_graph_0' type=dtype('float32') shape=['s0', 3]
----- subgraph ---- If - node_If_4 - att.else_branch=G2 -- level=1 --  -> neg_false_graph_0
Neg(x) -> neg_false_graph_0
output: name='neg_false_graph_0' type=dtype('float32') shape=['s0', 3]

script

FAILED

Detected that you are using FX to torch.jit.trace a dynamo-optimized function. This is not supported at the moment.

ControlFlowScan

forward

def forward(self, x):
    init = torch.zeros_like(x[0])
    carry, out = torch.ops.higher_order.scan(
        ControlFlowScan.add, [init], [x], reverse=False, additional_inputs=[]
    )
    return carry

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
ConstantOfShape(init7_s1_3, value=[0.0]) -> zeros_like
  Scan(zeros_like, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> output_0, scan#1
output: name='output_0' type=dtype('float32') shape=[3]
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_zeros_like,scan_0_x -> output_0,output_1
input: name='init_0_zeros_like' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_zeros_like, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Add(arg0_1, arg1_1) -> output_0
  Identity(output_0) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 3]
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
ConstantOfShape(init7_s1_3, value=[0.0]) -> zeros_like
  Scan(zeros_like, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> output_0, scan#1
output: name='output_0' type=dtype('float32') shape=[3]
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_zeros_like,scan_0_x -> output_0,output_1
input: name='init_0_zeros_like' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_zeros_like, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Add(arg0_1, arg1_1) -> output_0
  Identity(output_0) -> output_1
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

Unable to symbolically trace HigherOrderOperators

dynamo-ir

FAILED

Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps:
- If there is a missing ONNX function, implement it and register it to the registry.
- If there is an internal error during ONNX conversion, debug the error and summit a PR to PyTorch.
- Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model.

## Exception summary

<class 'torch.onnx._internal.exporter._errors.DispatchError'>: No ONNX function found for <torch._higher_order_ops.scan.ScanOp object at 0x7fd3f920e4e0>. Failure message: No decompositions registered for the real-valued input
⬆️
<class 'torch.onnx._internal.exporter._errors.ConversionError'>: Error when translating node %scan : [num_users=1] = call_function[target=torch.ops.higher_order.scan](args = (%scan_combine_graph_0, [%zeros_like], [%x], False, []), kwargs = {}). See the stack trace for more information.

(Refer to the full stack trace above for more information.)

script

FAILED

could not find kernel for HigherOrderOperator scan at dispatch key DispatchKey.??? (resolved from DispatchKey.???)

ControlFlowScan2Carried

forward

def forward(self, x):
    init1 = torch.zeros_like(x[0])
    init2 = torch.ones_like(x[0])
    carry1, carry2, out1, out2 = torch.ops.higher_order.scan(
        ControlFlowScan2Carried.add,
        [init1, init2],
        [x, x * 2],
        # dim=0,  # 01/31/2025, not supported anymore
        reverse=False,
        additional_inputs=[],
    )
    return carry1, carry2, out1, out2

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
ConstantOfShape(init7_s1_4, value=[1.0]) -> ones_like
ConstantOfShape(init7_s1_4, value=[0.0]) -> zeros_like
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(x, _reshape_init1_s_0) -> _onx_mul_x0
  Scan(zeros_like, ones_like, x, _onx_mul_x0, body=G1, num_scan_inputs=2, scan_input_directions=[0,0], scan_output_axes=[0,0], scan_output_directions=[0,0]) -> output_0, output_1, output_2, output_3
output: name='output_0' type=dtype('float32') shape=[4]
output: name='output_1' type=dtype('float32') shape=[4]
output: name='output_2' type=dtype('float32') shape=['batch', 4]
output: name='output_3' type=dtype('float32') shape=['batch', 4]
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_zeros_like,init_1_ones_like,scan_0_x,scan_1_mul -> output_0,output_1,output_2,output_3
input: name='init_0_zeros_like' type='NOTENSOR' shape=None
input: name='init_1_ones_like' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
input: name='scan_1_mul' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_zeros_like, init_1_ones_like, scan_0_x, scan_1_mul) -> output_0, output_1, output_2, output_3
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
output: name='output_2' type='NOTENSOR' shape=None
output: name='output_3' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
input: 'arg2_1'
input: 'arg3_1'
Add(arg0_1, arg2_1) -> output_0
  Identity(output_0) -> output_2
Mul(arg1_1, arg3_1) -> output_1
  Identity(output_1) -> output_3
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
output: name='output_2' type=? shape=?
output: name='output_3' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='init7_s1_4' type=int64 shape=(1,) -- array([4])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
ConstantOfShape(init7_s1_4, value=[1.0]) -> ones_like
ConstantOfShape(init7_s1_4, value=[0.0]) -> zeros_like
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(x, _reshape_init1_s_0) -> _onx_mul_x0
  Scan(zeros_like, ones_like, x, _onx_mul_x0, body=G1, num_scan_inputs=2, scan_input_directions=[0,0], scan_output_axes=[0,0], scan_output_directions=[0,0]) -> output_0, output_1, output_2, output_3
output: name='output_0' type=dtype('float32') shape=[4]
output: name='output_1' type=dtype('float32') shape=[4]
output: name='output_2' type=dtype('float32') shape=['batch', 4]
output: name='output_3' type=dtype('float32') shape=['batch', 4]
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_zeros_like,init_1_ones_like,scan_0_x,scan_1_mul -> output_0,output_1,output_2,output_3
input: name='init_0_zeros_like' type='NOTENSOR' shape=None
input: name='init_1_ones_like' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
input: name='scan_1_mul' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_zeros_like, init_1_ones_like, scan_0_x, scan_1_mul) -> output_0, output_1, output_2, output_3
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
output: name='output_2' type='NOTENSOR' shape=None
output: name='output_3' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
input: 'arg2_1'
input: 'arg3_1'
Add(arg0_1, arg2_1) -> output_0
  Identity(output_0) -> output_2
Mul(arg1_1, arg3_1) -> output_1
  Identity(output_1) -> output_3
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?
output: name='output_2' type=? shape=?
output: name='output_3' type=? shape=?

custom-tracing

FAILED

Unable to symbolically trace HigherOrderOperators

dynamo-ir

FAILED

Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps:
- If there is a missing ONNX function, implement it and register it to the registry.
- If there is an internal error during ONNX conversion, debug the error and summit a PR to PyTorch.
- Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model.

## Exception summary

<class 'torch.onnx._internal.exporter._errors.DispatchError'>: No ONNX function found for <torch._higher_order_ops.scan.ScanOp object at 0x7fd3f920e4e0>. Failure message: No decompositions registered for the real-valued input
⬆️
<class 'torch.onnx._internal.exporter._errors.ConversionError'>: Error when translating node %scan : [num_users=4] = call_function[target=torch.ops.higher_order.scan](args = (%scan_combine_graph_0, [%zeros_like, %ones_like], [%x, %mul], False, []), kwargs = {}). See the stack trace for more information.

(Refer to the full stack trace above for more information.)

script

FAILED

could not find kernel for HigherOrderOperator scan at dispatch key DispatchKey.??? (resolved from DispatchKey.???)

ControlFlowScanCDist

forward

def forward(self, x):
    carry, out = torch.ops.higher_order.scan(
        ControlFlowScanCDist.dist,
        [x],
        [x],
        # dim=0,  # 01/31/2025, not supported anymore
        reverse=False,
        additional_inputs=[],
    )
    return out

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
Scan(x, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'batch']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_x,scan_0_x -> output_0,output_1
input: name='init_0_x' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_x, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> reshape
    Sub(arg0_1, reshape) -> sub
      Mul(sub, sub) -> mul
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
Scan(x, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'batch']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_x,scan_0_x -> output_0,output_1
input: name='init_0_x' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_x, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> view
    Sub(arg0_1, view) -> sub_1
      Mul(sub_1, sub_1) -> mul_4
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul_4, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

Unable to symbolically trace HigherOrderOperators

dynamo-ir

FAILED

Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps:
- If there is a missing ONNX function, implement it and register it to the registry.
- If there is an internal error during ONNX conversion, debug the error and summit a PR to PyTorch.
- Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model.

## Exception summary

<class 'torch.onnx._internal.exporter._errors.DispatchError'>: No ONNX function found for <torch._higher_order_ops.scan.ScanOp object at 0x7fd3f920e4e0>. Failure message: No decompositions registered for the real-valued input
⬆️
<class 'torch.onnx._internal.exporter._errors.ConversionError'>: Error when translating node %scan : [num_users=1] = call_function[target=torch.ops.higher_order.scan](args = (%scan_combine_graph_0, [%x], [%x], False, []), kwargs = {}). See the stack trace for more information.

(Refer to the full stack trace above for more information.)

script

FAILED

could not find kernel for HigherOrderOperator scan at dispatch key DispatchKey.??? (resolved from DispatchKey.???)

ControlFlowScanCDist2

forward

def forward(self, x):
    z = torch.tensor([0], dtype=torch.float32)
    y = x.clone()
    out = torch.ops.higher_order.scan(
        ControlFlowScanCDist2.dist,
        [z],
        [x],
        # dim=0,  # 01/31/2025, not supported anymore
        reverse=False,
        additional_inputs=[y],
    )
    return out[1]

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_lifted_tensor_0' type=float32 shape=(1,) -- array([0.], dtype=float32)-- DynamoInterpret.placeholder.0
Identity(x) -> hidden_input_scan_0_clone
Scan(c_lifted_tensor_0, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'batch']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_detach_,scan_0_x -> output_0,output_1
input: name='init_0_detach_' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_detach_, scan_0_x, hidden_input_scan_0_clone) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
input: 'arg2_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> reshape
    Sub(arg2_1, reshape) -> sub
      Mul(sub, sub) -> mul
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_lifted_tensor_0' type=float32 shape=(1,) -- array([0.], dtype=float32)-- DynamoInterpret.placeholder.0
Identity(x) -> hidden_input_scan_0_clone_1
Scan(c_lifted_tensor_0, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'batch']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_clone,scan_0_x -> output_0,output_1
input: name='init_0_clone' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_clone, scan_0_x, hidden_input_scan_0_clone_1) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
input: 'arg2_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> view
    Sub(arg2_1, view) -> sub_1
      Mul(sub_1, sub_1) -> mul_4
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul_4, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

[CustomProxy(clone)] can only be of (<class 'torch.Tensor'>, <class 'int'>, <class 'torch.SymInt'>) but got (<class 'experimental_experiment.torch_interpreter.tracing.CustomProxy'>,)

dynamo-ir

FAILED

Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps:
- If there is a missing ONNX function, implement it and register it to the registry.
- If there is an internal error during ONNX conversion, debug the error and summit a PR to PyTorch.
- Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model.

## Exception summary

<class 'torch.onnx._internal.exporter._errors.DispatchError'>: No ONNX function found for <torch._higher_order_ops.scan.ScanOp object at 0x7fd3f920e4e0>. Failure message: No decompositions registered for the real-valued input
⬆️
<class 'torch.onnx._internal.exporter._errors.ConversionError'>: Error when translating node %scan : [num_users=1] = call_function[target=torch.ops.higher_order.scan](args = (%scan_combine_graph_0, [%clone], [%x], False, [%clone_1]), kwargs = {}). See the stack trace for more information.

(Refer to the full stack trace above for more information.)

script

FAILED

could not find kernel for HigherOrderOperator scan at dispatch key DispatchKey.??? (resolved from DispatchKey.???)

ControlFlowScanCDistXY

forward

def forward(self, x, y):
    carry, out = torch.ops.higher_order.scan(
        ControlFlowScanCDistXY.dist,
        [y],
        [x],
        # dim=0,  # 01/31/2025, not supported anymore
        reverse=False,
        additional_inputs=[],
    )
    return out

custom-fallback

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['x_rows', 'dim']
input: name='y' type=dtype('float32') shape=['y_rows', 'dim']
Scan(y, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['x_rows', 'y_rows']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_y,scan_0_x -> output_0,output_1
input: name='init_0_y' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_y, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> reshape
    Sub(arg0_1, reshape) -> sub
      Mul(sub, sub) -> mul
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-dec

opset: domain='' version=18
opset: domain='local_functions' version=1
input: name='x' type=dtype('float32') shape=['x_rows', 'dim']
input: name='y' type=dtype('float32') shape=['y_rows', 'dim']
Scan(y, x, body=G1, num_scan_inputs=1, scan_input_directions=[0], scan_output_axes=[0], scan_output_directions=[0]) -> scan#0, output_0
output: name='output_0' type=dtype('float32') shape=['x_rows', 'y_rows']
----- subgraph ---- Scan - scan - att.body=G1 -- level=1 -- init_0_y,scan_0_x -> output_0,output_1
input: name='init_0_y' type='NOTENSOR' shape=None
input: name='scan_0_x' type='NOTENSOR' shape=None
scan_combine_graph_0[local_functions](init_0_y, scan_0_x) -> output_0, output_1
output: name='output_0' type='NOTENSOR' shape=None
output: name='output_1' type='NOTENSOR' shape=None
----- function name=scan_combine_graph_0 domain=local_functions
----- doc_string: -- function_options=FunctionOptions(export_as_function=...
opset: domain='' version=18
input: 'arg0_1'
input: 'arg1_1'
Constant(value=[1, -1]) -> init7_s2_1_-1
  Reshape(arg1_1, init7_s2_1_-1) -> view
    Sub(arg0_1, view) -> sub_4
      Mul(sub_4, sub_4) -> mul_7
Constant(value=[1]) -> init7_s1_1
  ReduceSum(mul_7, init7_s1_1, keepdims=0) -> sum_1
    Sqrt(sum_1) -> output_1
Identity(arg0_1) -> output_0
output: name='output_0' type=? shape=?
output: name='output_1' type=? shape=?

custom-tracing

FAILED

Unable to symbolically trace HigherOrderOperators

dynamo-ir

FAILED

Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps:
- If there is a missing ONNX function, implement it and register it to the registry.
- If there is an internal error during ONNX conversion, debug the error and summit a PR to PyTorch.
- Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model.

## Exception summary

<class 'torch.onnx._internal.exporter._errors.DispatchError'>: No ONNX function found for <torch._higher_order_ops.scan.ScanOp object at 0x7fd3f920e4e0>. Failure message: No decompositions registered for the real-valued input
⬆️
<class 'torch.onnx._internal.exporter._errors.ConversionError'>: Error when translating node %scan : [num_users=1] = call_function[target=torch.ops.higher_order.scan](args = (%scan_combine_graph_0, [%y], [%x], False, []), kwargs = {}). See the stack trace for more information.

(Refer to the full stack trace above for more information.)

script

FAILED

could not find kernel for HigherOrderOperator scan at dispatch key DispatchKey.??? (resolved from DispatchKey.???)

CreateFromShape

forward

def forward(self, x):
    y = torch.ones((x.shape[0], x.shape[1] + 1))
    return y

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['dx', 'dy']
init: name='init7_s_1' type=int64 shape=() -- array([1])              -- shape_type_compute._cast_inputs.1(add)
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Shape(x, end=1, start=0) -> _shape_x0
Shape(x, end=2, start=1) -> _shape_x02
  Squeeze(_shape_x02) -> sym_size_int_3
    Add(sym_size_int_3, init7_s_1) -> _onx_add_sym_size_int_30
      Unsqueeze(_onx_add_sym_size_int_30, init7_s1_0) -> _onx_unsqueeze_add0
  Concat(_shape_x0, _onx_unsqueeze_add0, axis=0) -> _onx_concat_unsqueeze_sym_size_int_200
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int_200, value=[1.0]) -> output_0
output: name='output_0' type=dtype('float32') shape=['dx', 'dy+1']

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['dx', 'dy']
init: name='init7_s_1' type=int64 shape=() -- array([1])              -- shape_type_compute._cast_inputs.1(add)
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Shape(x, end=1, start=0) -> _shape_x0
Shape(x, end=2, start=1) -> _shape_x02
  Squeeze(_shape_x02) -> sym_size_int_3
    Add(sym_size_int_3, init7_s_1) -> _onx_add_sym_size_int_30
      Unsqueeze(_onx_add_sym_size_int_30, init7_s1_0) -> _onx_unsqueeze_add0
  Concat(_shape_x0, _onx_unsqueeze_add0, axis=0) -> _onx_concat_unsqueeze_sym_size_int_200
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int_200, value=[1.0]) -> output_0
output: name='output_0' type=dtype('float32') shape=['dx', 'dy+1']

custom-tracing

FAILED

ones(): argument 'size' (position 1) must be tuple of ints, but found element of type CustomProxy at pos 0

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 's1']
Constant(value=1.0) -> val_10
Shape(x, end=1, start=0) -> val_0
  Squeeze(val_0) -> sym_size_int_2
Shape(x, end=2, start=1) -> val_1
  Squeeze(val_1) -> sym_size_int_3
Constant(value=1) -> val_2
  Add(sym_size_int_3, val_2) -> add
Constant(value=[-1]) -> val_3
  Reshape(sym_size_int_2, val_3, allowzero=0) -> val_4
Constant(value=[-1]) -> val_5
  Reshape(add, val_5, allowzero=0) -> val_6
    Concat(val_4, val_6, axis=0) -> val_7
  Expand(val_10, val_7) -> ones
output: name='ones' type=dtype('float32') shape=['s0', 's1 + 1']

script

FAILED

number of input names provided (4) exceeded number of inputs (1)

CreateFromShapeThroughFunction

forward

def forward(self, x):
    dy1 = CreateFromShapeThroughFunction.add_one(x.shape[1])
    y = torch.ones((x.shape[0], dy1))
    return y

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['dx', 'dy']
init: name='init7_s_1' type=int64 shape=() -- array([1])              -- shape_type_compute._cast_inputs.1(add)
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Shape(x, end=1, start=0) -> _shape_x0
Shape(x, end=2, start=1) -> _shape_x02
  Squeeze(_shape_x02) -> sym_size_int_3
    Add(sym_size_int_3, init7_s_1) -> _onx_add_sym_size_int_30
      Unsqueeze(_onx_add_sym_size_int_30, init7_s1_0) -> _onx_unsqueeze_add0
  Concat(_shape_x0, _onx_unsqueeze_add0, axis=0) -> _onx_concat_unsqueeze_sym_size_int_200
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int_200, value=[1.0]) -> output_0
output: name='output_0' type=dtype('float32') shape=['dx', 'dy+1']

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['dx', 'dy']
init: name='init7_s_1' type=int64 shape=() -- array([1])              -- shape_type_compute._cast_inputs.1(add)
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Shape(x, end=1, start=0) -> _shape_x0
Shape(x, end=2, start=1) -> _shape_x02
  Squeeze(_shape_x02) -> sym_size_int_3
    Add(sym_size_int_3, init7_s_1) -> _onx_add_sym_size_int_30
      Unsqueeze(_onx_add_sym_size_int_30, init7_s1_0) -> _onx_unsqueeze_add0
  Concat(_shape_x0, _onx_unsqueeze_add0, axis=0) -> _onx_concat_unsqueeze_sym_size_int_200
    ConstantOfShape(_onx_concat_unsqueeze_sym_size_int_200, value=[1.0]) -> output_0
output: name='output_0' type=dtype('float32') shape=['dx', 'dy+1']

custom-tracing

FAILED

ones(): argument 'size' (position 1) must be tuple of ints, but found element of type CustomProxy at pos 0

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 's1']
Constant(value=1.0) -> val_10
Shape(x, end=1, start=0) -> val_0
  Squeeze(val_0) -> sym_size_int_2
Shape(x, end=2, start=1) -> val_1
  Squeeze(val_1) -> sym_size_int_3
Constant(value=1) -> val_2
  Add(sym_size_int_3, val_2) -> add
Constant(value=[-1]) -> val_3
  Reshape(sym_size_int_2, val_3, allowzero=0) -> val_4
Constant(value=[-1]) -> val_5
  Reshape(add, val_5, allowzero=0) -> val_6
    Concat(val_4, val_6, axis=0) -> val_7
  Expand(val_10, val_7) -> ones
output: name='ones' type=dtype('float32') shape=['s0', 's1 + 1']

script

FAILED

number of input names provided (4) exceeded number of inputs (1)

CropLastDimensionWithTensorContent

forward

def forward(self, x, shape):
    return x[..., : shape[0]]

custom-fallback

class GraphModule(torch.nn.Module):

def forward(self, L_x_: “f32[s0, s1, s2][s1*s2, s2, 1]cpu”, L_shape_: “i64[1][1]cpu”):

l_x_ = L_x_ l_shape_ = L_shape_

# File: /home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py:873 in forward, code: return x[…, : shape[0]]

getitem: “i64[][]cpu” = l_shape_[0]; l_shape_ = getitem = None

def forward(self, arg0_1: “f32[s0, s1, s2]”, arg1_1: “i64[1]”):

# File: /home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py:873 in forward, code: return x[…, : shape[0]]

select: “i64[]” = torch.ops.aten.select.int(arg1_1, 0, 0); arg1_1 = None item: “Sym(u0)” = torch.ops.aten.item.default(select); select = item = None

class GraphModule(torch.nn.Module):

def forward(self, L_x_: “f32[s0, s1, s2][s1*s2, s2, 1]cpu”, L_shape_: “i64[1][1]cpu”):

l_x_ = L_x_ l_shape_ = L_shape_

# File: /home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py:873 in forward, code: return x[…, : shape[0]]

getitem: “i64[][]cpu” = l_shape_[0]; l_shape_ = getitem = None

def forward(self, arg0_1: “f32[s0, s1, s2]”, arg1_1: “i64[1]”):

# File: /home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py:873 in forward, code: return x[…, : shape[0]]

select: “i64[]” = torch.ops.aten.select.int(arg1_1, 0, 0); arg1_1 = None item: “Sym(u0)” = torch.ops.aten.item.default(select); select = item = None

def forward(self, arg0_1: “f32[s0, s1, s2]”, arg1_1: “i64[1]”):

# No stacktrace found for following nodes select: “i64[]” = torch.ops.aten.select.int(arg1_1, 0, 0); arg1_1 = None _to_copy: “i32[]” = torch.ops.aten._to_copy.default(select, dtype = torch.int32); select = None _local_scalar_dense: “Sym(u0)” = torch.ops.aten._local_scalar_dense.default(_to_copy); _to_copy = None slice_1 = torch.ops.aten.slice.Tensor(arg0_1, 2, 0, _local_scalar_dense); arg0_1 = _local_scalar_dense = slice_1 = None

FAILED

None of the following options [ExportOptions(), ExportOptions(strict=False), ExportOptions(decomposition_table='default'), ExportOptions(strict=False, decomposition_table='default'), ExportOptions(dynamo=True), ExportOptions(decomposition_table='default', dynamo=True), ExportOptions(jit=True)] worked, args=(T1r3,T7r1), kwargs=None, exception=
-----
[(ExportOptions(),
  Unsupported('Dynamic slicing on data-dependent value is not supported\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 873, in forward\n    return x[..., : shape[0]]\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(strict=False),
  GuardOnDataDependentSymNode('Could not extract specialized integer from data-dependent expression u0 (unhinted: u0).  (Size-like symbols: none)\n\nCaused by: (_export/non_strict_utils.py:670 in __torch_function__)\nFor more information, run with TORCH_LOGS="dynamic"\nFor extended logs when we create symbols, also add TORCHDYNAMO_EXTENDED_DEBUG_CREATE_SYMBOL="u0"\nIf you suspect the guard was triggered from C++, add TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\nFor more debugging help, see https://docs.google.com/document/d/1HSuTTVvYH1pTew89Rtpeu84Ht3nQEFTYhAX3Ypa_xJs/edit?usp=sharing\n\nFor C++ stack trace, run with TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\n\nThe following call raised this error:\n  File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 873, in forward\n    return x[..., : shape[0]]\n')),
 (ExportOptions(decomposition_table='default'),
  Unsupported('Dynamic slicing on data-dependent value is not supported\n\nfrom user code:\n   File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 873, in forward\n    return x[..., : shape[0]]\n\nSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information\n')),
 (ExportOptions(strict=False, decomposition_table='default'),
  GuardOnDataDependentSymNode('Could not extract specialized integer from data-dependent expression u0 (unhinted: u0).  (Size-like symbols: none)\n\nCaused by: (_export/non_strict_utils.py:670 in __torch_function__)\nFor more information, run with TORCH_LOGS="dynamic"\nFor extended logs when we create symbols, also add TORCHDYNAMO_EXTENDED_DEBUG_CREATE_SYMBOL="u0"\nIf you suspect the guard was triggered from C++, add TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\nFor more debugging help, see https://docs.google.com/document/d/1HSuTTVvYH1pTew89Rtpeu84Ht3nQEFTYhAX3Ypa_xJs/edit?usp=sharing\n\nFor C++ stack trace, run with TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\n\nThe following call raised this error:\n  File "/home/xadupre/github/experimental-experiment/experimental_experiment/torch_interpreter/eval/model_cases.py", line 873, in forward\n    return x[..., : shape[0]]\n')),
 (ExportOptions(dynamo=True),
  UserError('Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs` has 2 elements, but `dynamic_shapes` has 1 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation')),
 (ExportOptions(decomposition_table='default', dynamo=True),
  UserError('Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs` has 2 elements, but `dynamic_shapes` has 1 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation')),
 (ExportOptions(jit=True),
  GuardOnDataDependentSymNode('Could not guard on data-dependent expression u0 < 0 (unhinted: u0 < 0).  (Size-like symbols: none)\n\nCaused by: (_decomp/decompositions.py:734 in slice_forward)\nFor more information, run with TORCH_LOGS="dynamic"\nFor extended logs when we create symbols, also add TORCHDYNAMO_EXTENDED_DEBUG_CREATE_SYMBOL="u0"\nIf you suspect the guard was triggered from C++, add TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\nFor more debugging help, see https://docs.google.com/document/d/1HSuTTVvYH1pTew89Rtpeu84Ht3nQEFTYhAX3Ypa_xJs/edit?usp=sharing\n\nFor C++ stack trace, run with TORCHDYNAMO_EXTENDED_DEBUG_CPP=1\n\nThe following call raised this error:\n  File "<string>", line 1, in <lambda>\n\n\nWhile executing %slice_tensor : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%x, 2, 0, %_local_scalar_dense_default, 1), kwargs = {})\nGraphModule: class GraphModule(torch.nn.Module):\n    def forward(self, x, shape):\n        # No stacktrace found for following nodes\n        select_int = torch.ops.aten.select.int(shape, 0, 0);  shape = None\n        _to_copy_default = torch.ops.aten._to_copy.default(select_int, dtype = torch.int32);  select_int = None\n        _local_scalar_dense_default = torch.ops.aten._local_scalar_dense.default(_to_copy_default);  _to_copy_default = None\n        slice_tensor = torch.ops.aten.slice.Tensor(x, 2, 0, _local_scalar_dense_default, 1);  x = _local_scalar_dense_default = None\n        return slice_tensor\n        \n\nOriginal traceback:\nNone'))]

custom-dec

FAILED

When `dynamic_shapes` is specified as a dict, its top-level keys must be the arg names ['x', 'shape'] of `inputs`, but here they are ['x']. Alternatively, you could also ignore arg names entirely and specify `dynamic_shapes` as a list/tuple matching `inputs`. For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4, 4]
input: name='shape' type=dtype('int64') shape=[1]
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='getitem_1_axis' type=int64 shape=(1,) -- array([-1])      -- DynamoInterpreter._getitem_slice.axis.1
init: name='getitem_1_step' type=int64 shape=(1,) -- array([1])       -- DynamoInterpreter._getitem_slice.3
Gather(shape, init7_s1_0) -> _onx_gather_shape0
  Slice(x, init7_s1_0, _onx_gather_shape0, getitem_1_axis, getitem_1_step) -> output
output: name='output' type=dtype('float32') shape=['d_output_0', 'd_output_1', 'd_output_2']

dynamo-ir

FAILED

Failed to export the model with torch.export. This is step 1/3 of exporting the model to ONNX. Next steps:
- Modify the model code for `torch.export.export` to succeed. Refer to https://pytorch.org/docs/stable/generated/exportdb/index.html for more information.
- Debug `torch.export.export` and summit a PR to PyTorch.
- Create an issue in the PyTorch GitHub repository against the *torch.export* component and attach the full error stack as well as reproduction scripts.

## Exception summary

<class 'torch._dynamo.exc.UserError'>: When `dynamic_shapes` is specified as a dict, its top-level keys must be the arg names ['x', 'shape'] of `inputs`, but here they are ['x']. Alternatively, you could also ignore arg names entirely and specify `dynamic_shapes` as a list/tuple matching `inputs`. For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

(Refer to the full stack trace above for more information.)

script

FAILED

number of input names provided (3) exceeded number of inputs (2)

CropLastDimensionWithTensorShape

forward

def forward(self, x, y):
    return x[..., : y.shape[0]]

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4, 4]
input: name='y' type=dtype('float32') shape=['crop']
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape
Shape(y, end=1, start=0) -> _shape_y0
  Slice(x, init7_s1_0, _shape_y0, init7_s1_2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4, 'crop']

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4, 4]
input: name='y' type=dtype('float32') shape=['crop']
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape
Shape(y, end=1, start=0) -> _shape_y0
  Slice(x, init7_s1_0, _shape_y0, init7_s1_2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4, 'crop']

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4, 4]
input: name='y' type=dtype('float32') shape=['crop']
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='getitem_1_axis' type=int64 shape=(1,) -- array([-1])      -- DynamoInterpreter._getitem_slice.axis.1
init: name='getitem_1_step' type=int64 shape=(1,) -- array([1])       -- DynamoInterpreter._getitem_slice.3
Shape(y) -> getattr_1
  Gather(getattr_1, init7_s1_0) -> _onx_gather_getattr_10
    Slice(x, init7_s1_0, _onx_gather_getattr_10, getitem_1_axis, getitem_1_step) -> output
output: name='output' type=dtype('float32') shape=['d_output_0', 'd_output_1', 'd_output_2']

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4, 4]
input: name='y' type=dtype('float32') shape=['s1']
Constant(value_ints=[1]) -> val_12
Shape(y, end=1, start=0) -> val_0
  Squeeze(val_0) -> sym_size_int_4
Constant(value=[0]) -> val_4
Constant(value_ints=[-1]) -> val_6
  Reshape(sym_size_int_4, val_6, allowzero=0) -> val_7
Constant(value=[2]) -> val_11
  Slice(x, val_4, val_7, val_11, val_12) -> slice_1
output: name='slice_1' type=dtype('float32') shape=['s0', 4, 's1']

script

FAILED

number of input names provided (3) exceeded number of inputs (2)

InplaceAdd

forward

def forward(self, x):
    x += self.bias
    return x

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
  Identity(output_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 4]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.get_attr.0
Add(x, bias) -> output
output: name='output' type=dtype('float32') shape=['batch', 4]

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
init: name='bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)
Add(x, bias) -> add_3
output: name='add_3' type=dtype('float32') shape=['s0', 4]

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

InplaceAdd2

forward

def forward(self, x):
    x.add_(self.bias)
    return x

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
  Identity(output_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 4]

custom-tracing

FAILED

Unable to interpret method 'aten_meth_add_', args=(x, bias), kwargs={}, dispatcher=None
--DEBUG--
[GraphBuilder-MOM] Message starts, there are 1 initializers, 0 nodes, 1 inputs, 1 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'bias': 1, 'x': 1}
_known_shapes={'bias': (1, 4), 'x': ('batch', 4)}
_known_value_shape={}
_known_constants=['bias']
_known_ranks={}
--TORCH-USERS--
    add_ -> {output}
    bias -> {add_}
    x -> {add_}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([3, 4])), '')) --- 1:2:('batch', 4):
    bias: ('run_node', ('', '')) --- 1:2:(1, 4):
    add_: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %bias : [num_users=1] = get_attr[target=bias]
    %add_ : [num_users=1] = call_method[target=add_](args = (%x, %bias), kwargs = {})
    return add_
-- process.progress --
node 2/4 target=add_
--
[GraphBuilder-MOM.make_tensor_input] x[1:batchx4]
[GraphBuilder-MOM.make_initializer] bias[torch.float32:torch.float32:[1.0, 1.0, 1.0, 1.0]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-MOM] Message completed, there are 1 initializers, 0 nodes, 1 inputs, 1 outputs.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
init: name='bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)
Add(x, bias) -> add_3
output: name='add_3' type=dtype('float32') shape=['s0', 4]

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

InplaceAdd_Mul

forward

def forward(self, x):
    x.add_(self.bias)
    return x * 2

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
Add(x, c_bias) -> add_
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(add_, _reshape_init1_s_0) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
Add(x, c_bias) -> output_0
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(output_0, _reshape_init1_s_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 4]

custom-tracing

FAILED

Unable to interpret method 'aten_meth_add_', args=(x, bias), kwargs={}, dispatcher=None
--DEBUG--
[GraphBuilder-QVG] Message starts, there are 1 initializers, 0 nodes, 1 inputs, 1 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'bias': 1, 'x': 1}
_known_shapes={'bias': (1, 4), 'x': ('batch', 4)}
_known_value_shape={}
_known_constants=['bias']
_known_ranks={}
--TORCH-USERS--
    add_ -> {mul}
    bias -> {add_}
    x -> {add_}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([3, 4])), '')) --- 1:2:('batch', 4):
    bias: ('run_node', ('', '')) --- 1:2:(1, 4):
    add_: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %bias : [num_users=1] = get_attr[target=bias]
    %add_ : [num_users=1] = call_method[target=add_](args = (%x, %bias), kwargs = {})
    %mul : [num_users=1] = call_function[target=operator.mul](args = (%add_, 2), kwargs = {})
    return mul
-- process.progress --
node 2/5 target=add_
--
[GraphBuilder-QVG.make_tensor_input] x[1:batchx4]
[GraphBuilder-QVG.make_initializer] bias[torch.float32:torch.float32:[1.0, 1.0, 1.0, 1.0]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-QVG] Message completed, there are 1 initializers, 0 nodes, 1 inputs, 1 outputs.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
init: name='bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)
Add(x, bias) -> add_3
Constant(value=2.0) -> scalar_tensor_default
  Mul(add_3, scalar_tensor_default) -> mul_4
output: name='mul_4' type=dtype('float32') shape=['s0', 4]

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

InplaceCloneAdd

forward

def forward(self, x):
    x = x.clone()
    x.add_(self.bias)
    return x

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
init: name='c_bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)-- DynamoInterpret.placeholder.0
Add(x, c_bias) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-tracing

FAILED

Unable to interpret method 'aten_meth_add_', args=(clone, bias), kwargs={}, dispatcher=None
--DEBUG--
[GraphBuilder-SUY] Message starts, there are 1 initializers, 1 nodes, 1 inputs, 1 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'bias': 1, 'clone': 1, 'x': 1}
_known_shapes={'bias': (1, 4), 'clone': ('batch', 4), 'x': ('batch', 4)}
_known_value_shape={}
_known_constants=['bias']
_known_ranks={}
--TORCH-USERS--
    add_ -> {output}
    bias -> {add_}
    clone -> {add_}
    x -> {clone}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([3, 4])), '')) --- 1:2:('batch', 4):
    clone: ('run_node', ('', '')) --- 1:2:('batch', 4):
    bias: ('run_node', ('', '')) --- 1:2:(1, 4):
    add_: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %clone : [num_users=1] = call_method[target=clone](args = (%x,), kwargs = {})
    %bias : [num_users=1] = get_attr[target=bias]
    %add_ : [num_users=1] = call_method[target=add_](args = (%clone, %bias), kwargs = {})
    return add_
-- process.progress --
node 3/5 target=add_
--
[GraphBuilder-SUY.make_tensor_input] x[1:batchx4]
[GraphBuilder-SUY.make_initializer] bias[torch.float32:torch.float32:[1.0, 1.0, 1.0, 1.0]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-SUY.make_node] .clone          [#:#   ] Identity:['x']->['clone']
[GraphBuilder-SUY] Message completed, there are 1 initializers, 1 nodes, 1 inputs, 1 outputs.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 4]
init: name='bias' type=float32 shape=(1, 4) -- array([1., 1., 1., 1.], dtype=float32)
Add(x, bias) -> add_6
output: name='add_6' type=dtype('float32') shape=['s0', 4]

script

FAILED

number of input names provided (3) exceeded number of inputs (1)

InplaceSetItemEllipsis_1

forward

def forward(self, index, update):
    copy = self.params.clone()
    copy[..., index] = update
    return copy

custom-fallback

FAILED

Issue with one input name and its associated dynamic shape dyn_name='x', input_name=index
--DEBUG--
[GraphBuilder-KNG] Message starts, there are 12 initializers, 18 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
   s0 = 's0'
   s0*8192 = 's0*8192'
   s1 = 's1'
   s2 = 's2'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_onx_add_add_mul__reshape_init7_s1_00000': 7,
 '_onx_add_mul__reshape_init7_s1_0000': 7,
 '_onx_expand_update0': 1,
 '_onx_gatherelements_init7_s32768_0': 7,
 '_onx_mul__reshape_init7_s1_000': 7,
 '_onx_mul__reshape_init7_s8192_00': 7,
 '_onx_scatterelements__reshape_clone00': 1,
 '_reshape_add_add_mul__reshape_init7_s1_000000': 7,
 '_reshape_clone0': 1,
 '_reshape_expand_update00': 1,
 '_reshape_index0': 7,
 '_reshape_init7_s1_00': 7,
 '_reshape_init7_s8192_0': 7,
 '_shape_index0': 7,
 '_shape_init7_s1_00': 7,
 '_shape_init7_s8192_20': 7,
 'add-_onx_mul__reshape_init7_s1_000': 7,
 'b_lifted_tensor_5': 1,
 'clone': 1,
 'index': 7,
 'index_put_': 1,
 'init7_s1_-1': 7,
 'init7_s1_0': 7,
 'init7_s1_32768': 7,
 'init7_s1_4': 7,
 'init7_s32768_': 7,
 'init7_s3_-1_1_1': 7,
 'init7_s3_1_-1_1': 7,
 'init7_s3_1_1_-1': 7,
 'init7_s3_1_8192_4': 7,
 'init7_s8192_': 7,
 'init7_s8192_2': 7,
 'output_0': 1,
 'update': 1}
_known_shapes={'_onx_add_add_mul__reshape_init7_s1_00000': (1, 8192, 's0'),
 '_onx_add_mul__reshape_init7_s1_0000': (1, 8192, 1),
 '_onx_concat__shape_init7_s1_000': (3,),
 '_onx_expand_update0': (1, 8192, 's0'),
 '_onx_gatherelements_init7_s32768_0': ('s0*8192',),
 '_onx_mul__reshape_init7_s1_000': (1, 1, 1),
 '_onx_mul__reshape_init7_s8192_00': (1, 8192, 1),
 '_onx_scatterelements__reshape_clone00': (32768,),
 '_reshape_add_add_mul__reshape_init7_s1_000000': ('s0*8192',),
 '_reshape_clone0': (32768,),
 '_reshape_expand_update00': ('s0*8192',),
 '_reshape_index0': (1, 1, 's0'),
 '_reshape_init7_s1_00': (1, 1, 1),
 '_reshape_init7_s8192_0': (1, 8192, 1),
 '_shape_index0': (1,),
 '_shape_init7_s1_00': (1,),
 '_shape_init7_s8192_20': (1,),
 'add-_onx_mul__reshape_init7_s1_000': (1, 1, 's0'),
 'b_lifted_tensor_5': (1, 8192, 4),
 'clone': (1, 8192, 4),
 'index': ('s0',),
 'index_put_': (1, 8192, 4),
 'init7_s1_-1': (1,),
 'init7_s1_0': (1,),
 'init7_s1_32768': (1,),
 'init7_s1_4': (1,),
 'init7_s32768_': (32768,),
 'init7_s3_-1_1_1': (3,),
 'init7_s3_1_-1_1': (3,),
 'init7_s3_1_1_-1': (3,),
 'init7_s3_1_8192_4': (3,),
 'init7_s8192_': (8192,),
 'init7_s8192_2': (8192,),
 'output_0': (1, 8192, 4),
 'update': ('s1', 's2')}
_known_value_shape={'_onx_concat__shape_init7_s1_000': (1, 8192, 's0'),
 '_shape_index0': ('s0',),
 '_shape_init7_s1_00': (1,),
 '_shape_init7_s8192_20': (8192,),
 'init7_s1_0': (0,),
 'init7_s1_32768': (32768,),
 'init7_s1_4': (4,),
 'init7_s8192_2': '(int,...)#8192'}
_known_constants=['_onx_mul__reshape_init7_s1_000',
 '_onx_mul__reshape_init7_s8192_00',
 '_reshape_clone0',
 '_reshape_init7_s1_00',
 '_reshape_init7_s8192_0',
 '_shape_init7_s1_00',
 '_shape_init7_s8192_20',
 'b_lifted_tensor_5',
 'init7_s1_-1',
 'init7_s1_0',
 'init7_s1_32768',
 'init7_s1_4',
 'init7_s32768_',
 'init7_s3_-1_1_1',
 'init7_s3_1_-1_1',
 'init7_s3_1_1_-1',
 'init7_s3_1_8192_4',
 'init7_s8192_',
 'init7_s8192_2']
_known_ranks={}
--TORCH-USERS--
    b_lifted_tensor_5 -> {clone}
    clone -> {index_put_}
    index -> {index_put_}
    index_put_ -> {output}
    output -> set()
    update -> {index_put_}
--TORCH-SHAPES--
    b_lifted_tensor_5: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 4])))) --- 1:3:(1, 8192, 4):
    index: ('run_node', ('', ('val', torch.int64, torch.Size([s0])))) --- 7:1:('s0',):
    update: ('run_node', ('', ('val', torch.float32, torch.Size([s1, s2])))) --- 1:2:('s1', 's2'):
    clone: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 4])))) --- 1:3:(1, 8192, 4):
    index_put_: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 4])))) --- 1:3:(1, 8192, 4):
    output: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(fallback=True)
-- process.graph_module --
graph():
    %b_lifted_tensor_5 : [num_users=1] = placeholder[target=b_lifted_tensor_5]
    %index : [num_users=1] = placeholder[target=index]
    %update : [num_users=1] = placeholder[target=update]
    %clone : [num_users=1] = call_function[target=torch.ops.aten.clone.default](args = (%b_lifted_tensor_5,), kwargs = {})
    %index_put_ : [num_users=1] = call_function[target=torch.ops.aten.index_put_.default](args = (%clone, [None, None, %index], %update), kwargs = {})
    return (index_put_,)
-- process.progress --
node 5/6 target=output
--
[GraphBuilder-KNG.make_tensor_input] index[7:s0]
[GraphBuilder-KNG.make_tensor_input] update[1:s1xs2]
[GraphBuilder-KNG.make_initializer] b_lifted_tensor_5[torch.float32:torch.float32] - SOURCE: DynamoInterpret.placeholder.0
[GraphBuilder-KNG.make_initializer] init7_s1_0[int64:int64:[0]] - SOURCE: Opset.make_node.1/Shape##Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s3_-1_1_1[int64:int64:[-1, 1, 1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s8192_[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-KNG.make_initializer] init7_s3_1_-1_1[int64:int64:[1, -1, 1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s3_1_1_-1[int64:int64:[1, 1, -1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s8192_2[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-KNG.make_initializer] init7_s1_32768[int64:int64:[32768]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s1_4[int64:int64:[4]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s1_-1[int64:int64:[-1]] - SOURCE: Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
[GraphBuilder-KNG.make_initializer] init7_s32768_[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-KNG.make_initializer] init7_s3_1_8192_4[int64:int64:[1, 8192, 4]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_ [##:#  ] Reshape:['init7_s1_0', 'init7_s3_-1_1_1']->['_reshape_init7_s1_00']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_2 [##:#  ] Reshape:['init7_s8192_', 'init7_s3_1_-1_1']->['_reshape_init7_s8192_0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_3 [##:#  ] Reshape:['index', 'init7_s3_1_1_-1']->['_reshape_index0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_4 [#:#   ] Shape:['init7_s1_0']->['_shape_init7_s1_00']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_5 [#:#   ] Shape:['init7_s8192_2']->['_shape_init7_s8192_20']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_6 [#:#   ] Shape:['index']->['_shape_index0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_7 [###:W ] Concat:['_shape_init7_s1_00', '_shape_init7_s8192_20', '_shape_index0']->['_onx_concat__shape_init7_s1_000']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_8 [#W:#  ] Expand:['update', '_onx_concat__shape_init7_s1_000']->['_onx_expand_update0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_9 [##:#  ] Mul:['_reshape_init7_s1_00', 'init7_s1_32768']->['_onx_mul__reshape_init7_s1_000']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_10 [##:#  ] Mul:['_reshape_init7_s8192_0', 'init7_s1_4']->['_onx_mul__reshape_init7_s8192_00']
[GraphBuilder-KNG.make_node] SwitchOrderBinaryPattern--index_put_3ioioi1x3v2_12 [##:#  ] Add:['_onx_mul__reshape_init7_s1_000', '_reshape_index0']->['add-_onx_mul__reshape_init7_s1_000']
[GraphBuilder-KNG.make_node] SwitchOrderBinaryPattern--index_put_3ioioi1x3v2_122 [##:#  ] Add:['add-_onx_mul__reshape_init7_s1_000', '_onx_mul__reshape_init7_s8192_00']->['_onx_add_add_mul__reshape_init7_s1_00000']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_13 [##:#  ] Reshape:['_onx_add_add_mul__reshape_init7_s1_00000', 'init7_s1_-1']->['_reshape_add_add_mul__reshape_init7_s1_000000']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_14 [##:#  ] GatherElements:['init7_s32768_', '_reshape_add_add_mul__reshape_init7_s1_000000']->['_onx_gatherelements_init7_s32768_0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_15 [##:#  ] Reshape:['_onx_expand_update0', 'init7_s1_-1']->['_reshape_expand_update00']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_16 [##:#  ] Reshape:['b_lifted_tensor_5', 'init7_s1_-1']->['_reshape_clone0']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_17 [###:# ] ScatterElements:['_reshape_clone0', '_onx_gatherelements_init7_s32768_0', '_reshape_expand_update00']->['_onx_scatterelements__reshape_clone00']
[GraphBuilder-KNG.make_node] index_put_3ioioi1x3v2_18 [##:#  ] Reshape:['_onx_scatterelements__reshape_clone00', 'init7_s3_1_8192_4']->['output_0']
[GraphBuilder-KNG.make_tensor_output] output_0[1:1x8192x4]
[GraphBuilder-KNG] Message completed, there are 12 initializers, 18 nodes, 2 inputs, 2 outputs.

custom-dec

FAILED

When `dynamic_shapes` is specified as a dict, its top-level keys must be the arg names ['index', 'update'] of `inputs`, but here they are ['x']. Alternatively, you could also ignore arg names entirely and specify `dynamic_shapes` as a list/tuple matching `inputs`. For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

custom-tracing

FAILED

setitem is not implemented when indices=(Ellipsis, 'index') and rank is unknown or not equal to the number of indices
--DEBUG--
[GraphBuilder-RWQ] Message starts, there are 1 initializers, 0 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_tensor_constant0': 1, 'index': 7, 'update': 1}
_known_shapes={'_tensor_constant0': (1, 8192, 4), 'index': (4,), 'update': (8192, 4)}
_known_value_shape={}
_known_constants=['_tensor_constant0']
_known_ranks={}
--TORCH-USERS--
    _tensor_constant0 -> {setitem}
    index -> {setitem}
    setitem -> {output}
    update -> {setitem}
--TORCH-SHAPES--
    index: ('run_node', (('example_value', torch.int64, torch.Size([4])), '')) --- 7:1:(4,):
    update: ('run_node', (('example_value', torch.float32, torch.Size([8192, 4])), '')) --- 1:2:(8192, 4):
    _tensor_constant0: ('run_node', ('', '')) --- 1:3:(1, 8192, 4):
    setitem: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %index : [num_users=1] = placeholder[target=index]
    %update : [num_users=1] = placeholder[target=update]
    %_tensor_constant0 : [num_users=1] = get_attr[target=_tensor_constant0]
    %setitem : [num_users=1] = call_function[target=operator.setitem](args = (%_tensor_constant0, (Ellipsis, %index), %update), kwargs = {})
    return setitem
-- process.progress --
node 3/5 target=<built-in function setitem>
--
[GraphBuilder-RWQ.make_tensor_input] index[7:4]
[GraphBuilder-RWQ.make_tensor_input] update[1:8192x4]
[GraphBuilder-RWQ.make_initializer] _tensor_constant0[torch.float32:torch.float32] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-RWQ] Message completed, there are 1 initializers, 0 nodes, 2 inputs, 2 outputs.

dynamo-ir

FAILED

[ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. In Node, ("node_Unsqueeze_2", Unsqueeze, "", -1) : ("","val_0": tensor(int64),) -> ("val_1",) , Error Node (node_Unsqueeze_2)'s input 0 is marked single but has an empty string in the graph

script

FAILED

number of input names provided (4) exceeded number of inputs (2)

InplaceSetItemEllipsis_2

forward

def forward(self, index, update):
    copy = self.params.clone()
    copy[..., index] = update
    return copy

custom-fallback

FAILED

Issue with one input name and its associated dynamic shape dyn_name='x', input_name=index
--DEBUG--
[GraphBuilder-WBO] Message starts, there are 12 initializers, 18 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
   s0 = 's0'
   s0*8192 = 's0*8192'
   s1 = 's1'
   s2 = 's2'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_onx_add_add_mul__reshape_init7_s1_00000': 7,
 '_onx_add_mul__reshape_init7_s1_0000': 7,
 '_onx_expand_update0': 1,
 '_onx_gatherelements_init7_s49152_0': 7,
 '_onx_mul__reshape_init7_s1_000': 7,
 '_onx_mul__reshape_init7_s8192_00': 7,
 '_onx_scatterelements__reshape_clone00': 1,
 '_reshape_add_add_mul__reshape_init7_s1_000000': 7,
 '_reshape_clone0': 1,
 '_reshape_expand_update00': 1,
 '_reshape_index0': 7,
 '_reshape_init7_s1_00': 7,
 '_reshape_init7_s8192_0': 7,
 '_shape_index0': 7,
 '_shape_init7_s1_00': 7,
 '_shape_init7_s8192_20': 7,
 'add-_onx_mul__reshape_init7_s1_000': 7,
 'b_lifted_tensor_5': 1,
 'clone': 1,
 'index': 7,
 'index_put_': 1,
 'init7_s1_-1': 7,
 'init7_s1_0': 7,
 'init7_s1_49152': 7,
 'init7_s1_6': 7,
 'init7_s3_-1_1_1': 7,
 'init7_s3_1_-1_1': 7,
 'init7_s3_1_1_-1': 7,
 'init7_s3_1_8192_6': 7,
 'init7_s49152_': 7,
 'init7_s8192_': 7,
 'init7_s8192_2': 7,
 'output_0': 1,
 'update': 1}
_known_shapes={'_onx_add_add_mul__reshape_init7_s1_00000': (1, 8192, 's0'),
 '_onx_add_mul__reshape_init7_s1_0000': (1, 8192, 1),
 '_onx_concat__shape_init7_s1_000': (3,),
 '_onx_expand_update0': (1, 8192, 's0'),
 '_onx_gatherelements_init7_s49152_0': ('s0*8192',),
 '_onx_mul__reshape_init7_s1_000': (1, 1, 1),
 '_onx_mul__reshape_init7_s8192_00': (1, 8192, 1),
 '_onx_scatterelements__reshape_clone00': (49152,),
 '_reshape_add_add_mul__reshape_init7_s1_000000': ('s0*8192',),
 '_reshape_clone0': (49152,),
 '_reshape_expand_update00': ('s0*8192',),
 '_reshape_index0': (1, 1, 's0'),
 '_reshape_init7_s1_00': (1, 1, 1),
 '_reshape_init7_s8192_0': (1, 8192, 1),
 '_shape_index0': (1,),
 '_shape_init7_s1_00': (1,),
 '_shape_init7_s8192_20': (1,),
 'add-_onx_mul__reshape_init7_s1_000': (1, 1, 's0'),
 'b_lifted_tensor_5': (1, 8192, 6),
 'clone': (1, 8192, 6),
 'index': ('s0',),
 'index_put_': (1, 8192, 6),
 'init7_s1_-1': (1,),
 'init7_s1_0': (1,),
 'init7_s1_49152': (1,),
 'init7_s1_6': (1,),
 'init7_s3_-1_1_1': (3,),
 'init7_s3_1_-1_1': (3,),
 'init7_s3_1_1_-1': (3,),
 'init7_s3_1_8192_6': (3,),
 'init7_s49152_': (49152,),
 'init7_s8192_': (8192,),
 'init7_s8192_2': (8192,),
 'output_0': (1, 8192, 6),
 'update': ('s1', 's2')}
_known_value_shape={'_onx_concat__shape_init7_s1_000': (1, 8192, 's0'),
 '_shape_index0': ('s0',),
 '_shape_init7_s1_00': (1,),
 '_shape_init7_s8192_20': (8192,),
 'init7_s1_0': (0,),
 'init7_s1_49152': (49152,),
 'init7_s1_6': (6,),
 'init7_s8192_2': '(int,...)#8192'}
_known_constants=['_onx_mul__reshape_init7_s1_000',
 '_onx_mul__reshape_init7_s8192_00',
 '_reshape_clone0',
 '_reshape_init7_s1_00',
 '_reshape_init7_s8192_0',
 '_shape_init7_s1_00',
 '_shape_init7_s8192_20',
 'b_lifted_tensor_5',
 'init7_s1_-1',
 'init7_s1_0',
 'init7_s1_49152',
 'init7_s1_6',
 'init7_s3_-1_1_1',
 'init7_s3_1_-1_1',
 'init7_s3_1_1_-1',
 'init7_s3_1_8192_6',
 'init7_s49152_',
 'init7_s8192_',
 'init7_s8192_2']
_known_ranks={}
--TORCH-USERS--
    b_lifted_tensor_5 -> {clone}
    clone -> {index_put_}
    index -> {index_put_}
    index_put_ -> {output}
    output -> set()
    update -> {index_put_}
--TORCH-SHAPES--
    b_lifted_tensor_5: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 6])))) --- 1:3:(1, 8192, 6):
    index: ('run_node', ('', ('val', torch.int64, torch.Size([s0])))) --- 7:1:('s0',):
    update: ('run_node', ('', ('val', torch.float32, torch.Size([s1, s2])))) --- 1:2:('s1', 's2'):
    clone: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 6])))) --- 1:3:(1, 8192, 6):
    index_put_: ('run_node', ('', ('val', torch.float32, torch.Size([1, 8192, 6])))) --- 1:3:(1, 8192, 6):
    output: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(fallback=True)
-- process.graph_module --
graph():
    %b_lifted_tensor_5 : [num_users=1] = placeholder[target=b_lifted_tensor_5]
    %index : [num_users=1] = placeholder[target=index]
    %update : [num_users=1] = placeholder[target=update]
    %clone : [num_users=1] = call_function[target=torch.ops.aten.clone.default](args = (%b_lifted_tensor_5,), kwargs = {})
    %index_put_ : [num_users=1] = call_function[target=torch.ops.aten.index_put_.default](args = (%clone, [None, None, %index], %update), kwargs = {})
    return (index_put_,)
-- process.progress --
node 5/6 target=output
--
[GraphBuilder-WBO.make_tensor_input] index[7:s0]
[GraphBuilder-WBO.make_tensor_input] update[1:s1xs2]
[GraphBuilder-WBO.make_initializer] b_lifted_tensor_5[torch.float32:torch.float32] - SOURCE: DynamoInterpret.placeholder.0
[GraphBuilder-WBO.make_initializer] init7_s1_0[int64:int64:[0]] - SOURCE: Opset.make_node.1/Shape##Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s3_-1_1_1[int64:int64:[-1, 1, 1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s8192_[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-WBO.make_initializer] init7_s3_1_-1_1[int64:int64:[1, -1, 1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s3_1_1_-1[int64:int64:[1, 1, -1]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s8192_2[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-WBO.make_initializer] init7_s1_49152[int64:int64:[49152]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s1_6[int64:int64:[6]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s1_-1[int64:int64:[-1]] - SOURCE: Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
[GraphBuilder-WBO.make_initializer] init7_s49152_[int64:int64] - SOURCE: Opset.make_node.0
[GraphBuilder-WBO.make_initializer] init7_s3_1_8192_6[int64:int64:[1, 8192, 6]] - SOURCE: Opset.make_node.1/Shape
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_ [##:#  ] Reshape:['init7_s1_0', 'init7_s3_-1_1_1']->['_reshape_init7_s1_00']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_2 [##:#  ] Reshape:['init7_s8192_', 'init7_s3_1_-1_1']->['_reshape_init7_s8192_0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_3 [##:#  ] Reshape:['index', 'init7_s3_1_1_-1']->['_reshape_index0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_4 [#:#   ] Shape:['init7_s1_0']->['_shape_init7_s1_00']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_5 [#:#   ] Shape:['init7_s8192_2']->['_shape_init7_s8192_20']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_6 [#:#   ] Shape:['index']->['_shape_index0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_7 [###:W ] Concat:['_shape_init7_s1_00', '_shape_init7_s8192_20', '_shape_index0']->['_onx_concat__shape_init7_s1_000']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_8 [#W:#  ] Expand:['update', '_onx_concat__shape_init7_s1_000']->['_onx_expand_update0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_9 [##:#  ] Mul:['_reshape_init7_s1_00', 'init7_s1_49152']->['_onx_mul__reshape_init7_s1_000']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_10 [##:#  ] Mul:['_reshape_init7_s8192_0', 'init7_s1_6']->['_onx_mul__reshape_init7_s8192_00']
[GraphBuilder-WBO.make_node] SwitchOrderBinaryPattern--index_put_3ioioi1x3v2_12 [##:#  ] Add:['_onx_mul__reshape_init7_s1_000', '_reshape_index0']->['add-_onx_mul__reshape_init7_s1_000']
[GraphBuilder-WBO.make_node] SwitchOrderBinaryPattern--index_put_3ioioi1x3v2_122 [##:#  ] Add:['add-_onx_mul__reshape_init7_s1_000', '_onx_mul__reshape_init7_s8192_00']->['_onx_add_add_mul__reshape_init7_s1_00000']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_13 [##:#  ] Reshape:['_onx_add_add_mul__reshape_init7_s1_00000', 'init7_s1_-1']->['_reshape_add_add_mul__reshape_init7_s1_000000']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_14 [##:#  ] GatherElements:['init7_s49152_', '_reshape_add_add_mul__reshape_init7_s1_000000']->['_onx_gatherelements_init7_s49152_0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_15 [##:#  ] Reshape:['_onx_expand_update0', 'init7_s1_-1']->['_reshape_expand_update00']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_16 [##:#  ] Reshape:['b_lifted_tensor_5', 'init7_s1_-1']->['_reshape_clone0']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_17 [###:# ] ScatterElements:['_reshape_clone0', '_onx_gatherelements_init7_s49152_0', '_reshape_expand_update00']->['_onx_scatterelements__reshape_clone00']
[GraphBuilder-WBO.make_node] index_put_3ioioi1x3v2_18 [##:#  ] Reshape:['_onx_scatterelements__reshape_clone00', 'init7_s3_1_8192_6']->['output_0']
[GraphBuilder-WBO.make_tensor_output] output_0[1:1x8192x6]
[GraphBuilder-WBO] Message completed, there are 12 initializers, 18 nodes, 2 inputs, 2 outputs.

custom-dec

FAILED

When `dynamic_shapes` is specified as a dict, its top-level keys must be the arg names ['index', 'update'] of `inputs`, but here they are ['x']. Alternatively, you could also ignore arg names entirely and specify `dynamic_shapes` as a list/tuple matching `inputs`. For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

custom-tracing

FAILED

setitem is not implemented when indices=(Ellipsis, 'index') and rank is unknown or not equal to the number of indices
--DEBUG--
[GraphBuilder-TPG] Message starts, there are 1 initializers, 0 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_tensor_constant0': 1, 'index': 7, 'update': 1}
_known_shapes={'_tensor_constant0': (1, 8192, 6), 'index': (4,), 'update': (8192, 4)}
_known_value_shape={}
_known_constants=['_tensor_constant0']
_known_ranks={}
--TORCH-USERS--
    _tensor_constant0 -> {setitem}
    index -> {setitem}
    setitem -> {output}
    update -> {setitem}
--TORCH-SHAPES--
    index: ('run_node', (('example_value', torch.int64, torch.Size([4])), '')) --- 7:1:(4,):
    update: ('run_node', (('example_value', torch.float32, torch.Size([8192, 4])), '')) --- 1:2:(8192, 4):
    _tensor_constant0: ('run_node', ('', '')) --- 1:3:(1, 8192, 6):
    setitem: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %index : [num_users=1] = placeholder[target=index]
    %update : [num_users=1] = placeholder[target=update]
    %_tensor_constant0 : [num_users=1] = get_attr[target=_tensor_constant0]
    %setitem : [num_users=1] = call_function[target=operator.setitem](args = (%_tensor_constant0, (Ellipsis, %index), %update), kwargs = {})
    return setitem
-- process.progress --
node 3/5 target=<built-in function setitem>
--
[GraphBuilder-TPG.make_tensor_input] index[7:4]
[GraphBuilder-TPG.make_tensor_input] update[1:8192x4]
[GraphBuilder-TPG.make_initializer] _tensor_constant0[torch.float32:torch.float32] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-TPG] Message completed, there are 1 initializers, 0 nodes, 2 inputs, 2 outputs.

dynamo-ir

FAILED

[ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. In Node, ("node_Unsqueeze_2", Unsqueeze, "", -1) : ("","val_0": tensor(int64),) -> ("val_1",) , Error Node (node_Unsqueeze_2)'s input 0 is marked single but has an empty string in the graph

script

FAILED

number of input names provided (4) exceeded number of inputs (2)

InplaceSetItemMask

forward

def forward(self, x):
    mask = x.to(bool)
    x[mask] = 2
    return x

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 3]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([2.], dtype=float32)-- DynamoInterpret.placeholder.0
Cast(x, to=9) -> to
  Where(to, c_lifted_tensor_0, x) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 3, 3]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3, 3]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([2.], dtype=float32)-- DynamoInterpret.placeholder.0
Cast(x, to=9) -> _to_copy
  Where(_to_copy, c_lifted_tensor_0, x) -> output_0
    Identity(output_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 3, 3]

custom-tracing

FAILED

Unexpected type <class 'int'> for name.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3, 3]
Cast(x, to=9) -> _to_copy
Constant(value=2.0) -> clone
  Where(_to_copy, clone, x) -> index_put
output: name='index_put' type=dtype('float32') shape=['s0', 3, 3]

script

FAILED

number of input names provided (2) exceeded number of inputs (1)

InplaceSetItemSquare

forward

def forward(self, x):
    x[:2, :3] = 1
    return x

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
        Identity(output_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 5]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
        Identity(output_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 5]

custom-tracing

FAILED

Unexpected type <class 'int'> for name.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 5]
Constant(value=0) -> val_0
Constant(value=1) -> val_19
Constant(value=[0]) -> val_26
Constant(value=[2]) -> val_29
Constant(value=[0]) -> val_32
Constant(value_ints=[1]) -> val_33
  Slice(x, val_26, val_29, val_32, val_33) -> slice_3
    Transpose(slice_3, perm=[1,0]) -> val_45
Constant(value=-1) -> val_42
Constant(value=[[0], [1],...) -> val_43
Constant(value=[[1.0, 1.0...) -> val_44
  ScatterND(val_45, val_43, val_44, reduction=b'none') -> val_46
    Transpose(val_46, perm=[1,0]) -> slice_scatter
Constant(value_ints=[0]) -> val_47
Shape(x, start=0) -> val_48
  Gather(val_48, val_0, axis=0) -> val_49
  Range(val_0, val_49, val_19) -> val_50
Constant(value=[0]) -> val_51
Constant(value=[2]) -> val_52
Constant(value=[1]) -> val_53
  Slice(val_50, val_51, val_52, val_47, val_53) -> val_54
  Unsqueeze(val_54, val_42) -> val_55
    ScatterND(x, val_55, slice_scatter, reduction=b'none') -> slice_scatter_1
output: name='slice_scatter_1' type=dtype('float32') shape=['s0', 5]

script

FAILED

number of input names provided (5) exceeded number of inputs (1)

InplaceSetItemSquareAdd

forward

def forward(self, x):
    x[:2, :3] = 1
    return x + 2

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.0
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Add(output_0, _reshape_init1_s_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 5]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.0
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Add(output_0, _reshape_init1_s_0) -> output_1
output: name='output_1' type=dtype('float32') shape=['batch', 5]

custom-tracing

FAILED

Unexpected type <class 'int'> for name.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 5]
Constant(value=0) -> val_0
Constant(value=1) -> val_19
Constant(value=[0]) -> val_26
Constant(value=[2]) -> val_29
Constant(value=[0]) -> val_32
Constant(value_ints=[1]) -> val_33
  Slice(x, val_26, val_29, val_32, val_33) -> slice_3
    Transpose(slice_3, perm=[1,0]) -> val_45
Constant(value=-1) -> val_42
Constant(value=[[0], [1],...) -> val_43
Constant(value=[[1.0, 1.0...) -> val_44
  ScatterND(val_45, val_43, val_44, reduction=b'none') -> val_46
    Transpose(val_46, perm=[1,0]) -> slice_scatter
Constant(value_ints=[0]) -> val_47
Shape(x, start=0) -> val_48
  Gather(val_48, val_0, axis=0) -> val_49
  Range(val_0, val_49, val_19) -> val_50
Constant(value=[0]) -> val_51
Constant(value=[2]) -> val_52
Constant(value=[1]) -> val_53
  Slice(val_50, val_51, val_52, val_47, val_53) -> val_54
  Unsqueeze(val_54, val_42) -> val_55
    ScatterND(x, val_55, slice_scatter, reduction=b'none') -> slice_scatter_1
Constant(value=2.0) -> scalar_tensor_default
  Add(slice_scatter_1, scalar_tensor_default) -> add
output: name='add' type=dtype('float32') shape=['s0', 5]

script

FAILED

number of input names provided (5) exceeded number of inputs (1)

InplaceSetItemSquareAdd2

forward

def forward(self, x):
    x[:2, :3] = 1
    return x + 2, x + 3

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.0
init: name='init1_s_2' type=float32 shape=() -- array([3.], dtype=float32)-- shape_type_compute._cast_inputs.0
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Add(output_0, _reshape_init1_s_0) -> output_1
Reshape(init1_s_2, init7_s1_1) -> _reshape_init1_s_20
  Add(output_0, _reshape_init1_s_20) -> output_2
output: name='output_1' type=dtype('float32') shape=['batch', 5]
output: name='output_2' type=dtype('float32') shape=['batch', 5]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 5]
init: name='c_lifted_tensor_0' type=float32 shape=() -- array([1.], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_3' type=int64 shape=(1,) -- array([3])           -- Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s3_0_1_2' type=int64 shape=(3,) -- array([0, 1, 2]) -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init1_s_' type=float32 shape=() -- array([2.], dtype=float32)-- shape_type_compute._cast_inputs.0
init: name='init1_s_2' type=float32 shape=() -- array([3.], dtype=float32)-- shape_type_compute._cast_inputs.0
Concat(init7_s1_0, init7_s1_1, axis=0) -> SliceSlicePattern_init7_s1_1_axis
Concat(init7_s1_0, init7_s1_0, axis=0) -> SliceSlicePattern_init7_s1_0_start
Concat(init7_s1_2, init7_s1_3, axis=0) -> SliceSlicePattern_init7_s1_3_end
  Slice(x, SliceSlicePattern_init7_s1_0_start, SliceSlicePattern_init7_s1_3_end, SliceSlicePattern_init7_s1_1_axis) -> slice_2
    Shape(slice_2) -> _shape_slice_20
      Expand(c_lifted_tensor_0, _shape_slice_20) -> fill
        Transpose(fill, perm=[1,0]) -> _onx_transpose_fill0
Slice(x, init7_s1_0, init7_s1_2, init7_s1_0) -> slice_3
  Transpose(slice_3, perm=[1,0]) -> _onx_transpose_slice_30
Reshape(init7_s3_0_1_2, init7_s2_-1_1) -> _reshape_init7_s3_0_1_20
  ScatterND(_onx_transpose_slice_30, _reshape_init7_s3_0_1_20, _onx_transpose_fill0) -> _onx_scatternd_transpose_slice_300
    Transpose(_onx_scatternd_transpose_slice_300, perm=[1,0]) -> slice_scatter
Shape(x) -> _shape_x0
  Gather(_shape_x0, init7_s1_0) -> _onx_gather__shape_x00
    Range(init7_s1_0, _onx_gather__shape_x00, init7_s1_1) -> _onx_range_init7_s1_00
      Slice(_onx_range_init7_s1_00, init7_s1_0, init7_s1_2, init7_s1_0, init7_s1_1) -> _onx_slice_range_init7_s1_000
        Reshape(_onx_slice_range_init7_s1_000, init7_s2_-1_1) -> _reshape_slice_range_init7_s1_0000
      ScatterND(x, _reshape_slice_range_init7_s1_0000, slice_scatter) -> output_0
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Add(output_0, _reshape_init1_s_0) -> output_1
Reshape(init1_s_2, init7_s1_1) -> _reshape_init1_s_20
  Add(output_0, _reshape_init1_s_20) -> output_2
output: name='output_1' type=dtype('float32') shape=['batch', 5]
output: name='output_2' type=dtype('float32') shape=['batch', 5]

custom-tracing

FAILED

Unexpected type <class 'int'> for name.

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
opset: domain='pkg.onnxscript.torch_lib' version=1
input: name='x' type=dtype('float32') shape=['s0', 5]
Constant(value=0) -> val_0
Constant(value=1) -> val_19
Constant(value=[0]) -> val_26
Constant(value=[2]) -> val_29
Constant(value=[0]) -> val_32
Constant(value_ints=[1]) -> val_33
  Slice(x, val_26, val_29, val_32, val_33) -> slice_3
    Transpose(slice_3, perm=[1,0]) -> val_45
Constant(value=-1) -> val_42
Constant(value=[[0], [1],...) -> val_43
Constant(value=[[1.0, 1.0...) -> val_44
  ScatterND(val_45, val_43, val_44, reduction=b'none') -> val_46
    Transpose(val_46, perm=[1,0]) -> slice_scatter
Constant(value_ints=[0]) -> val_47
Shape(x, start=0) -> val_48
  Gather(val_48, val_0, axis=0) -> val_49
  Range(val_0, val_49, val_19) -> val_50
Constant(value=[0]) -> val_51
Constant(value=[2]) -> val_52
Constant(value=[1]) -> val_53
  Slice(val_50, val_51, val_52, val_47, val_53) -> val_54
  Unsqueeze(val_54, val_42) -> val_55
    ScatterND(x, val_55, slice_scatter, reduction=b'none') -> slice_scatter_1
Constant(value=2.0) -> scalar_tensor_default
  Add(slice_scatter_1, scalar_tensor_default) -> add
Constant(value=3.0) -> scalar_tensor_default_1
  Add(slice_scatter_1, scalar_tensor_default_1) -> add_4
output: name='add' type=dtype('float32') shape=['s0', 5]
output: name='add_4' type=dtype('float32') shape=['s0', 5]

script

FAILED

number of input names provided (5) exceeded number of inputs (1)

SignatureFloat1

forward

def forward(self, x, alpha: float = 2.0):
    return torch.sigmoid(self.linear(x)) - self.buff * alpha

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='alpha' type=dtype('float32') shape=[1]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init1_s_' type=float32 shape=() -- array([1.5], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.096, -0.078,  0.498], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.19], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(b_buff, _reshape_init1_s_0) -> _onx_mul_b_buff0
    Sub(sigmoid, _onx_mul_b_buff0) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='alpha' type=dtype('float32') shape=[1]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init1_s_' type=float32 shape=() -- array([1.5], dtype=float32)-- shape_type_compute._cast_inputs.1(mul_Tensor)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([0.028, 0.108, 0.377], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.452], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
Reshape(init1_s_, init7_s1_1) -> _reshape_init1_s_0
  Mul(b_buff, _reshape_init1_s_0) -> _onx_mul_b_buff0
    Sub(sigmoid, _onx_mul_b_buff0) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

FAILED

Unable to interpret method 'aten_meth_mul', args=(buff, alpha), kwargs={}, dispatcher=None
--DEBUG--
[GraphBuilder-TKY] Message starts, there are 3 initializers, 7 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=[0]
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes=({0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>},
 None)
_known_types={'_sub_Linear__onx_matmul_input_10': 1,
 '_sub_Linear__onx_transpose_weight0': 1,
 '_sub_Linear_input_1': 1,
 '_sub_Linear_linear': 1,
 '_sub_Linear_output': 1,
 'alpha': 1,
 'buff': 1,
 'linear': 1,
 'linear.bias': 1,
 'linear.weight': 1,
 'sigmoid': 1,
 'x': 1}
_known_shapes={'_sub_Linear__onx_matmul_input_10': ('batch', 1),
 '_sub_Linear__onx_transpose_weight0': (3, 1),
 '_sub_Linear_input_1': ('batch', 3),
 '_sub_Linear_linear': ('batch', 1),
 '_sub_Linear_output': ('batch', 1),
 'alpha': (),
 'buff': (1,),
 'linear': ('batch', 1),
 'linear.bias': (1,),
 'linear.weight': (1, 3),
 'sigmoid': ('batch', 1),
 'x': ('batch', 3)}
_known_value_shape={}
_known_constants=['_sub_Linear__onx_transpose_weight0', 'buff', 'linear.bias', 'linear.weight']
_known_ranks={}
--TORCH-USERS--
    alpha -> {mul}
    buff -> {mul}
    linear -> {sigmoid}
    mul -> {sub}
    sigmoid -> {sub}
    x -> {linear}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([4, 3])), '')) --- 1:2:('batch', 3):
    alpha: ('run_node', (('example_value', torch.float32, torch.Size([])), '')) --- 1:0:():
    linear: ('run_node', ('', '')) --- 1:2:('batch', 1):
    sigmoid: ('run_node', ('', '')) --- 1:2:('batch', 1):
    buff: ('run_node', ('', '')) --- 1:1:(1,):
    mul: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %alpha : float [num_users=1] = placeholder[target=alpha](default=2.0)
    %linear : [num_users=1] = call_module[target=linear](args = (%x,), kwargs = {})
    %sigmoid : [num_users=1] = call_function[target=torch.sigmoid](args = (%linear,), kwargs = {})
    %buff : [num_users=1] = get_attr[target=buff]
    %mul : [num_users=1] = call_method[target=mul](args = (%buff, %alpha), kwargs = {})
    %sub : [num_users=1] = call_function[target=operator.sub](args = (%sigmoid, %mul), kwargs = {})
    return sub
-- process.progress --
node 5/8 target=mul
--
[GraphBuilder-TKY.make_tensor_input] x[1:batchx3]
[GraphBuilder-TKY.make_tensor_input] alpha[1:]
[GraphBuilder-TKY.make_initializer] linear.weight[torch.float32:torch.float32:[-0.5548827052116394, -0.03955712169408798, -0.4261837601661682]] - SOURCE: GraphBuilder.make_nodes/fromlinear.weight##DynamoInterpret.get_attr.1/P(linear.weight)
[GraphBuilder-TKY.make_initializer] linear.bias[torch.float32:torch.float32:[-0.23177239298820496]] - SOURCE: GraphBuilder.make_nodes/fromlinear.bias##DynamoInterpret.get_attr.1/P(linear.bias)
[GraphBuilder-TKY.make_initializer] buff[torch.float32:torch.float32:[0.5]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-TKY.make_node] .make_nodes     [#:#   ] Identity:['x']->['_sub_Linear_input_1']
[GraphBuilder-TKY.make_node] linear          [#:#   ] Transpose:['linear.weight']->['_sub_Linear__onx_transpose_weight0']
[GraphBuilder-TKY.make_node] Opset           [##:#  ] MatMul:['_sub_Linear_input_1', '_sub_Linear__onx_transpose_weight0']->['_sub_Linear__onx_matmul_input_10']
[GraphBuilder-TKY.make_node] Opset2          [##:#  ] Add:['_sub_Linear__onx_matmul_input_10', 'linear.bias']->['_sub_Linear_linear']
[GraphBuilder-TKY.make_node] .output         [#:#   ] Identity:['_sub_Linear_linear']->['_sub_Linear_output']
[GraphBuilder-TKY.make_node] .make_nodes2    [#:#   ] Identity:['_sub_Linear_output']->['linear']
[GraphBuilder-TKY.make_node] sigmoid         [#:#   ] Sigmoid:['linear']->['sigmoid']
[GraphBuilder-TKY] Message completed, there are 3 initializers, 7 nodes, 2 inputs, 2 outputs.

dynamo-ir

FAILED

Input mismatch, inputs[0]=(T1r2,float) but names=['x'], model=SignatureFloat1, export='dynamo-ir'

script

FAILED

unable to convert dynamic shapes ({0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, None)

SignatureInt1

forward

def forward(self, x, i: int = 2):
    return torch.sigmoid(self.linear(x)) - self.buff + x[:, i : i + 1]

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='i' type=dtype('int64') shape=[1]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([0.568, 0.017, 0.519], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.188], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub
Slice(x, init7_s1_1, init7_s1_2, init7_s1_1) -> slice_2
  Add(sub, slice_2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='i' type=dtype('int64') shape=[1]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_2' type=int64 shape=(1,) -- array([2])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([ 0.489, -0.134,  0.232], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.251], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub_2
Slice(x, init7_s1_1, init7_s1_2, init7_s1_1) -> slice_2
  Add(sub_2, slice_2) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

FAILED

[ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Concat node. Name:'_getitem_slicenSD' Status Message: /home/xadupre/github/onnxruntime/onnxruntime/core/providers/cpu/tensor/concat.cc:139 onnxruntime::common::Status onnxruntime::ConcatBase::PrepareForCompute(onnxruntime::OpKernelContext*, const InlinedTensorsVector&, onnxruntime::Prepare&) const input_rank == reference_rank was false. Ranks of input data are different, cannot concatenate them. expected rank: 1 got: 2

dynamo-ir

FAILED

Input mismatch, inputs[0]=(T1r2,int) but names=['x'], model=SignatureInt1, export='dynamo-ir'

script

FAILED

unable to convert dynamic shapes ({0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, None)

SignatureInt2

forward

def forward(self, x, i: int = 2):
    return torch.sigmoid(self.linear(x)) - self.buff + x[:, i]

custom-fallback

FAILED

None of the following options [ExportOptions(), ExportOptions(strict=False), ExportOptions(decomposition_table='default'), ExportOptions(strict=False, decomposition_table='default'), ExportOptions(dynamo=True), ExportOptions(decomposition_table='default', dynamo=True), ExportOptions(jit=True)] worked, args=(T1r2,int), kwargs=None, exception=
-----
[(ExportOptions(),
  RuntimeError('Unable to convert model <class \'experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt2\'>, type(args)=<class \'tuple\'>, type(args[0])=<class \'torch.Tensor\'>, strict=True, input_names=None\n--\ndynamic_shapes={\'x\': {0: <class \'experimental_experiment.torch_interpreter.eval.model_cases.batch\'>}, \'i\': None}\n--\ne=Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'x\'].size()[0] in the specified range satisfy the generated guard L[\'x\'].size()[0] != 9223372036854775807.\n\n--\neee=None\n---exported-program---\ngraph():\n    %p_linear_weight : [num_users=1] = placeholder[target=p_linear_weight]\n    %p_linear_bias : [num_users=1] = placeholder[target=p_linear_bias]\n    %b_buff : [num_users=1] = placeholder[target=b_buff]\n    %x : [num_users=2] = placeholder[target=x]\n    %i : [num_users=0] = placeholder[target=i]\n    %linear : [num_users=1] = call_function[target=torch.ops.aten.linear.default](args = (%x, %p_linear_weight, %p_linear_bias), kwargs = {})\n    %sigmoid : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%linear,), kwargs = {})\n    %sub : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%sigmoid, %b_buff), kwargs = {})\n    %slice_1 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%x, 0, 0, 9223372036854775807), kwargs = {})\n    %select : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%slice_1, 1, 1), kwargs = {})\n    %add : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%sub, %select), kwargs = {})\n    return (add,)')),
 (ExportOptions(strict=False),
  RuntimeError('Unable to convert model <class \'experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt2\'>, type(args)=<class \'tuple\'>, type(args[0])=<class \'torch.Tensor\'>, strict=False, input_names=None\n--\ndynamic_shapes={\'x\': {0: <class \'experimental_experiment.torch_interpreter.eval.model_cases.batch\'>}, \'i\': None}\n--\ne=Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'args\'][0][0].size()[0] in the specified range satisfy the generated guard L[\'args\'][0][0].size()[0] != 9223372036854775807.\n--\neee=None\n---exported-program---\ngraph():\n    %p_linear_weight : [num_users=1] = placeholder[target=p_linear_weight]\n    %p_linear_bias : [num_users=1] = placeholder[target=p_linear_bias]\n    %b_buff : [num_users=1] = placeholder[target=b_buff]\n    %x : [num_users=2] = placeholder[target=x]\n    %i : [num_users=0] = placeholder[target=i]\n    %linear : [num_users=1] = call_function[target=torch.ops.aten.linear.default](args = (%x, %p_linear_weight, %p_linear_bias), kwargs = {})\n    %sigmoid : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%linear,), kwargs = {})\n    %sub : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%sigmoid, %b_buff), kwargs = {})\n    %slice_1 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%x, 0, 0, 9223372036854775807), kwargs = {})\n    %select : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%slice_1, 1, 1), kwargs = {})\n    %add : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%sub, %select), kwargs = {})\n    return (add,)')),
 (ExportOptions(decomposition_table='default'),
  RuntimeError('Unable to convert model <class \'experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt2\'>, type(args)=<class \'tuple\'>, type(args[0])=<class \'torch.Tensor\'>, strict=True, input_names=None\n--\ndynamic_shapes={\'x\': {0: <class \'experimental_experiment.torch_interpreter.eval.model_cases.batch\'>}, \'i\': None}\n--\ne=Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'x\'].size()[0] in the specified range satisfy the generated guard L[\'x\'].size()[0] != 9223372036854775807.\n\n--\neee=None\n---exported-program---\ngraph():\n    %p_linear_weight : [num_users=1] = placeholder[target=p_linear_weight]\n    %p_linear_bias : [num_users=1] = placeholder[target=p_linear_bias]\n    %b_buff : [num_users=1] = placeholder[target=b_buff]\n    %x : [num_users=2] = placeholder[target=x]\n    %i : [num_users=0] = placeholder[target=i]\n    %linear : [num_users=1] = call_function[target=torch.ops.aten.linear.default](args = (%x, %p_linear_weight, %p_linear_bias), kwargs = {})\n    %sigmoid : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%linear,), kwargs = {})\n    %sub : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%sigmoid, %b_buff), kwargs = {})\n    %slice_1 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%x, 0, 0, 9223372036854775807), kwargs = {})\n    %select : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%slice_1, 1, 1), kwargs = {})\n    %add : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%sub, %select), kwargs = {})\n    return (add,)')),
 (ExportOptions(strict=False, decomposition_table='default'),
  RuntimeError('Unable to convert model <class \'experimental_experiment.torch_interpreter.eval.model_cases.SignatureInt2\'>, type(args)=<class \'tuple\'>, type(args[0])=<class \'torch.Tensor\'>, strict=False, input_names=None\n--\ndynamic_shapes={\'x\': {0: <class \'experimental_experiment.torch_interpreter.eval.model_cases.batch\'>}, \'i\': None}\n--\ne=Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'args\'][0][0].size()[0] in the specified range satisfy the generated guard L[\'args\'][0][0].size()[0] != 9223372036854775807.\n--\neee=None\n---exported-program---\ngraph():\n    %p_linear_weight : [num_users=1] = placeholder[target=p_linear_weight]\n    %p_linear_bias : [num_users=1] = placeholder[target=p_linear_bias]\n    %b_buff : [num_users=1] = placeholder[target=b_buff]\n    %x : [num_users=2] = placeholder[target=x]\n    %i : [num_users=0] = placeholder[target=i]\n    %linear : [num_users=1] = call_function[target=torch.ops.aten.linear.default](args = (%x, %p_linear_weight, %p_linear_bias), kwargs = {})\n    %sigmoid : [num_users=1] = call_function[target=torch.ops.aten.sigmoid.default](args = (%linear,), kwargs = {})\n    %sub : [num_users=1] = call_function[target=torch.ops.aten.sub.Tensor](args = (%sigmoid, %b_buff), kwargs = {})\n    %slice_1 : [num_users=1] = call_function[target=torch.ops.aten.slice.Tensor](args = (%x, 0, 0, 9223372036854775807), kwargs = {})\n    %select : [num_users=1] = call_function[target=torch.ops.aten.select.int](args = (%slice_1, 1, 1), kwargs = {})\n    %add : [num_users=1] = call_function[target=torch.ops.aten.add.Tensor](args = (%sub, %select), kwargs = {})\n    return (add,)')),
 (ExportOptions(dynamo=True),
  ConstraintViolationError('Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'x\'].size()[0] in the specified range satisfy the generated guard L[\'x\'].size()[0] != 9223372036854775807.\n')),
 (ExportOptions(decomposition_table='default', dynamo=True),
  ConstraintViolationError('Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".\n  - Not all values of batch = L[\'x\'].size()[0] in the specified range satisfy the generated guard L[\'x\'].size()[0] != 9223372036854775807.\n')),
 (ExportOptions(jit=True),
  RuntimeError("Type 'Tuple[Tensor, int]' cannot be traced. Only Tensors and (possibly nested) Lists, Dicts, and Tuples of Tensors can be traced"))]

custom-dec

FAILED

Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".
  - Not all values of batch = L['x'].size()[0] in the specified range satisfy the generated guard L['x'].size()[0] != 9223372036854775807.

custom-tracing

FAILED

One index is given as an integer i but this requires to append a node 'Squeeze' after this one and this is not yet implemented. You can replace the integer by `i:i+1`
--DEBUG--
[GraphBuilder-EDK] Message starts, there are 5 initializers, 10 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'}]}
dynamic_dimensions_source_flat=['x']
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'i': None,
 'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'_sub_Linear__onx_matmul_input_10': 1,
 '_sub_Linear__onx_transpose_weight0': 1,
 '_sub_Linear_input_1': 1,
 '_sub_Linear_linear': 1,
 '_sub_Linear_output': 1,
 'buff': 1,
 'getitem_axis': 7,
 'getitem_axis_0': 7,
 'getitem_end': 7,
 'getitem_shape': 7,
 'i': 7,
 'linear': 1,
 'linear.bias': 1,
 'linear.weight': 1,
 'sigmoid': 1,
 'sub': 1,
 'x': 1}
_known_shapes={'_sub_Linear__onx_matmul_input_10': ('batch', 1),
 '_sub_Linear__onx_transpose_weight0': (3, 1),
 '_sub_Linear_input_1': ('batch', 3),
 '_sub_Linear_linear': ('batch', 1),
 '_sub_Linear_output': ('batch', 1),
 'buff': (1,),
 'getitem_axis': (2,),
 'getitem_axis_0': (1,),
 'getitem_end': (1,),
 'getitem_shape': (2,),
 'i': (),
 'linear': ('batch', 1),
 'linear.bias': (1,),
 'linear.weight': (1, 3),
 'sigmoid': ('batch', 1),
 'sub': ('batch', 1),
 'x': ('batch', 3)}
_known_value_shape={'getitem_shape': ('batch', 3)}
_known_constants=['_sub_Linear__onx_transpose_weight0',
 'buff',
 'getitem_axis',
 'getitem_axis_0',
 'linear.bias',
 'linear.weight']
_known_ranks={}
--TORCH-USERS--
    buff -> {sub}
    getitem -> {add}
    i -> {getitem}
    linear -> {sigmoid}
    sigmoid -> {sub}
    sub -> {add}
    x -> {linear, getitem}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([4, 3])), '')) --- 1:2:('batch', 3):
    i: ('run_node', (('example_value', torch.int64, torch.Size([])), '')) --- 7:0:():
    linear: ('run_node', ('', '')) --- 1:2:('batch', 1):
    sigmoid: ('run_node', ('', '')) --- 1:2:('batch', 1):
    buff: ('run_node', ('', '')) --- 1:1:(1,):
    sub: ('run_node', ('', '')) --- 1:2:('batch', 1):
    getitem: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=2] = placeholder[target=x]
    %i : int [num_users=1] = placeholder[target=i](default=2)
    %linear : [num_users=1] = call_module[target=linear](args = (%x,), kwargs = {})
    %sigmoid : [num_users=1] = call_function[target=torch.sigmoid](args = (%linear,), kwargs = {})
    %buff : [num_users=1] = get_attr[target=buff]
    %sub : [num_users=1] = call_function[target=operator.sub](args = (%sigmoid, %buff), kwargs = {})
    %getitem : [num_users=1] = call_function[target=operator.getitem](args = (%x, (slice(None, None, None), %i)), kwargs = {})
    %add : [num_users=1] = call_function[target=operator.add](args = (%sub, %getitem), kwargs = {})
    return add
-- process.progress --
node 6/9 target=<built-in function getitem>
--
[GraphBuilder-EDK.make_tensor_input] x[1:batchx3]
[GraphBuilder-EDK.make_tensor_input] i[7:]
[GraphBuilder-EDK.make_initializer] linear.weight[torch.float32:torch.float32:[0.02789284661412239, -0.11262331902980804, -0.1434551477432251]] - SOURCE: GraphBuilder.make_nodes/fromlinear.weight##DynamoInterpret.get_attr.1/P(linear.weight)
[GraphBuilder-EDK.make_initializer] linear.bias[torch.float32:torch.float32:[-0.37545549869537354]] - SOURCE: GraphBuilder.make_nodes/fromlinear.bias##DynamoInterpret.get_attr.1/P(linear.bias)
[GraphBuilder-EDK.make_initializer] buff[torch.float32:torch.float32:[0.5]] - SOURCE: DynamoInterpret.get_attr.0
[GraphBuilder-EDK.make_initializer] getitem_axis[int64:int64:[0, 1]] - SOURCE: DynamoInterpreter._getitem_slice.axis.1
[GraphBuilder-EDK.make_initializer] getitem_axis_0[int64:int64:[0]] - SOURCE: DynamoInterpreter._getitem_slice.axis.2
[GraphBuilder-EDK.make_node] .make_nodes     [#:#   ] Identity:['x']->['_sub_Linear_input_1']
[GraphBuilder-EDK.make_node] linear          [#:#   ] Transpose:['linear.weight']->['_sub_Linear__onx_transpose_weight0']
[GraphBuilder-EDK.make_node] Opset           [##:#  ] MatMul:['_sub_Linear_input_1', '_sub_Linear__onx_transpose_weight0']->['_sub_Linear__onx_matmul_input_10']
[GraphBuilder-EDK.make_node] Opset2          [##:#  ] Add:['_sub_Linear__onx_matmul_input_10', 'linear.bias']->['_sub_Linear_linear']
[GraphBuilder-EDK.make_node] .output         [#:#   ] Identity:['_sub_Linear_linear']->['_sub_Linear_output']
[GraphBuilder-EDK.make_node] .make_nodes2    [#:#   ] Identity:['_sub_Linear_output']->['linear']
[GraphBuilder-EDK.make_node] sigmoid         [#:#   ] Sigmoid:['linear']->['sigmoid']
[GraphBuilder-EDK.make_node] sub             [##:#  ] Sub:['sigmoid', 'buff']->['sub']
[GraphBuilder-EDK.make_node] _getitem_slicenA [#:#   ] Shape:['x']->['getitem_shape']
[GraphBuilder-EDK.make_node] _getitem_slicenB [##:#  ] GatherElements:['getitem_shape', 'getitem_axis_0']->['getitem_end']
[GraphBuilder-EDK] Message completed, there are 5 initializers, 10 nodes, 2 inputs, 2 outputs.

dynamo-ir

FAILED

Failed to export the model with torch.export. This is step 1/3 of exporting the model to ONNX. Next steps:
- Modify the model code for `torch.export.export` to succeed. Refer to https://pytorch.org/docs/stable/generated/exportdb/index.html for more information.
- Debug `torch.export.export` and summit a PR to PyTorch.
- Create an issue in the PyTorch GitHub repository against the *torch.export* component and attach the full error stack as well as reproduction scripts.

## Exception summary

<class 'torch._dynamo.exc.UserError'>: Constraints violated (batch)! For more information, run with TORCH_LOGS="+dynamic".
  - Not all values of batch = L['args'][0][0].size()[0] in the specified range satisfy the generated guard L['args'][0][0].size()[0] != 9223372036854775807.

(Refer to the full stack trace above for more information.)

script

FAILED

unable to convert dynamic shapes {'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, 'i': None}

SignatureListFixedLength

forward

def forward(self, x, lx: list):
    return (
        torch.sigmoid(self.linear(x)) - self.buff + lx[0] * lx[1].sum(axis=1, keepdim=True)
    )

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([ 0.531,  0.483, -0.046], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.537], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub
    Add(sub, mul) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([ 0.187, -0.343, -0.448], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.315], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
ReduceSum(lx_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(lx_0, sum_1) -> mul_4
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub_2
    Add(sub_2, mul_4) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx' type='NOTENSOR' shape=None
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.505, -0.071, -0.47 ], dtype=float32)-- GraphBuilder.make_nodes/fromlinear.weight##DynamoInterpret.get_attr.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.385], dtype=float32)-- GraphBuilder.make_nodes/fromlinear.bias##DynamoInterpret.get_attr.1/P(linear.bias)
init: name='buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.get_attr.0
init: name='init7_s_0' type=int64 shape=() -- array([0])              -- DynamoInterpreter.getitem.1
init: name='init7_s_1' type=int64 shape=() -- array([1])              -- DynamoInterpreter.getitem.1
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
Reshape(linear.weight, init7_s2_-1_1) -> _sub_Linear__onx_transpose_weight0
  Reshape(_sub_Linear__onx_transpose_weight0, init7_s2_1_-1) -> GemmTransposePattern--_sub_Linear__onx_transpose_weight0
    Gemm(x, GemmTransposePattern--_sub_Linear__onx_transpose_weight0, linear.bias, transB=1) -> _sub_Linear_linear
      Sigmoid(_sub_Linear_linear) -> sigmoid
        Sub(sigmoid, buff) -> sub
SequenceAt(lx, init7_s_0) -> getitem
SequenceAt(lx, init7_s_1) -> getitem_1
  ReduceSum(getitem_1, init7_s1_1, keepdims=1) -> sum_1
  Mul(getitem, sum_1) -> mul
    Add(sub, mul) -> output
output: name='output' type=dtype('float32') shape=['batch', 1]

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3]
input: name='lx_0' type=dtype('float32') shape=['s0', 1]
input: name='lx_1' type=dtype('float32') shape=['s0', 2]
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.346, -0.519,  0.411], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.332], dtype=float32)
init: name='buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)
Constant(value=[1]) -> val_3
  ReduceSum(lx_1, val_3, noop_with_empty_axes=0, keepdims=1) -> sum_1
    Mul(lx_0, sum_1) -> mul_4
Gemm(x, linear.weight, linear.bias, beta=1.00, transB=1, alpha=1.00, transA=0) -> linear
  Sigmoid(linear) -> sigmoid
    Sub(sigmoid, buff) -> sub_2
      Add(sub_2, mul_4) -> add_15
output: name='add_15' type=dtype('float32') shape=['s0', 1]

script

FAILED

unable to convert dynamic shapes {'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, 'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}

SignatureListFixedWithNone

forward

def forward(self, lx):
    x = lx[0]
    if lx[1] is not None:
        x += lx[1]
    if lx[2] is not None:
        x += lx[2]
    return x

custom-fallback

FAILED

None of the following options [ExportOptions(), ExportOptions(strict=False), ExportOptions(decomposition_table='default'), ExportOptions(strict=False, decomposition_table='default'), ExportOptions(dynamo=True), ExportOptions(decomposition_table='default', dynamo=True), ExportOptions(jit=True)] worked, args=(#3[T1r2,T1r2,None],), kwargs=None, exception=
-----
[(ExportOptions(),
  RuntimeError("Unable to convert model <class 'experimental_experiment.torch_interpreter.eval.model_cases.SignatureListFixedWithNone'>, type(args)=<class 'tuple'>, type(args[0])=<class 'list'>, strict=True, input_names=None\n--\ndynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}\n--\ne=Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation\n--\neee=None\n---exported-program---\ngraph():\n    %lx_0 : [num_users=1] = placeholder[target=lx_0]\n    %lx_1 : [num_users=1] = placeholder[target=lx_1]\n    %lx_2 : [num_users=0] = placeholder[target=lx_2]\n    %add_ : [num_users=1] = call_function[target=torch.ops.aten.add_.Tensor](args = (%lx_0, %lx_1), kwargs = {})\n    return (add_,)")),
 (ExportOptions(strict=False),
  RuntimeError("Unable to convert model <class 'experimental_experiment.torch_interpreter.eval.model_cases.SignatureListFixedWithNone'>, type(args)=<class 'tuple'>, type(args[0])=<class 'list'>, strict=False, input_names=None\n--\ndynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}\n--\ne=Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation\n--\neee=None\n---exported-program---\ngraph():\n    %lx_0 : [num_users=1] = placeholder[target=lx_0]\n    %lx_1 : [num_users=1] = placeholder[target=lx_1]\n    %lx_2 : [num_users=0] = placeholder[target=lx_2]\n    %add_ : [num_users=1] = call_function[target=torch.ops.aten.add_.Tensor](args = (%lx_0, %lx_1), kwargs = {})\n    return (add_,)")),
 (ExportOptions(decomposition_table='default'),
  RuntimeError("Unable to convert model <class 'experimental_experiment.torch_interpreter.eval.model_cases.SignatureListFixedWithNone'>, type(args)=<class 'tuple'>, type(args[0])=<class 'list'>, strict=True, input_names=None\n--\ndynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}\n--\ne=Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation\n--\neee=None\n---exported-program---\ngraph():\n    %lx_0 : [num_users=1] = placeholder[target=lx_0]\n    %lx_1 : [num_users=1] = placeholder[target=lx_1]\n    %lx_2 : [num_users=0] = placeholder[target=lx_2]\n    %add_ : [num_users=1] = call_function[target=torch.ops.aten.add_.Tensor](args = (%lx_0, %lx_1), kwargs = {})\n    return (add_,)")),
 (ExportOptions(strict=False, decomposition_table='default'),
  RuntimeError("Unable to convert model <class 'experimental_experiment.torch_interpreter.eval.model_cases.SignatureListFixedWithNone'>, type(args)=<class 'tuple'>, type(args[0])=<class 'list'>, strict=False, input_names=None\n--\ndynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}\n--\ne=Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation\n--\neee=None\n---exported-program---\ngraph():\n    %lx_0 : [num_users=1] = placeholder[target=lx_0]\n    %lx_1 : [num_users=1] = placeholder[target=lx_1]\n    %lx_2 : [num_users=0] = placeholder[target=lx_2]\n    %add_ : [num_users=1] = call_function[target=torch.ops.aten.add_.Tensor](args = (%lx_0, %lx_1), kwargs = {})\n    return (add_,)")),
 (ExportOptions(dynamo=True),
  UserError("Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation")),
 (ExportOptions(decomposition_table='default', dynamo=True),
  UserError("Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements\nFor more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation")),
 (ExportOptions(jit=True),
  RuntimeError("Type 'Tuple[List[Optional[Tensor]]]' cannot be traced. Only Tensors and (possibly nested) Lists, Dicts, and Tuples of Tensors can be traced"))]

custom-dec

FAILED

Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements
For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

custom-tracing

FAILED

Unable to create an input 'lx' with type #3[T1r2,T1r2,None]
--DEBUG--
[GraphBuilder-FHW] Message starts, there are 0 initializers, 0 nodes, 0 inputs, 0 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = WrapSym(batch)
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': ('lx', 0)},
           {'axis': 0, 'input_name': ('lx', 1)}]}
dynamic_dimensions_source_flat=[('lx', 0), ('lx', 1)]
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>},
        {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}
_known_types={}
_known_shapes={}
_known_value_shape={}
_known_constants=[]
_known_ranks={}
--TORCH-USERS--
    lx -> {getitem_2, getitem_3, getitem, getitem_1, getitem_4}
--TORCH-SHAPES--
    lx: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %lx : [num_users=5] = placeholder[target=lx]
    %getitem : [num_users=1] = call_function[target=operator.getitem](args = (%lx, 0), kwargs = {})
    %getitem_1 : [num_users=0] = call_function[target=operator.getitem](args = (%lx, 1), kwargs = {})
    %getitem_2 : [num_users=1] = call_function[target=operator.getitem](args = (%lx, 1), kwargs = {})
    %add : [num_users=1] = call_function[target=operator.add](args = (%getitem, %getitem_2), kwargs = {})
    %getitem_3 : [num_users=0] = call_function[target=operator.getitem](args = (%lx, 2), kwargs = {})
    %getitem_4 : [num_users=1] = call_function[target=operator.getitem](args = (%lx, 2), kwargs = {})
    %add_1 : [num_users=1] = call_function[target=operator.add](args = (%add, %getitem_4), kwargs = {})
    return add_1
-- process.progress --
node 0/9 target=lx
--
[GraphBuilder-FHW] Message completed, there are 0 initializers, 0 nodes, 0 inputs, 0 outputs.

dynamo-ir

FAILED

Failed to export the model with torch.export. This is step 1/3 of exporting the model to ONNX. Next steps:
- Modify the model code for `torch.export.export` to succeed. Refer to https://pytorch.org/docs/stable/generated/exportdb/index.html for more information.
- Debug `torch.export.export` and summit a PR to PyTorch.
- Create an issue in the PyTorch GitHub repository against the *torch.export* component and attach the full error stack as well as reproduction scripts.

## Exception summary

<class 'torch._dynamo.exc.UserError'>: Detected mismatch between the structure of `inputs` and `dynamic_shapes`: `inputs['lx']` has 3 elements, but `dynamic_shapes['lx']` has 2 elements
For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#dynamic-shapes-validation

(Refer to the full stack trace above for more information.)

script

FAILED

unable to convert dynamic shapes {'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}

SignatureListVariableLength

forward

def forward(self, x, lx: list):
    t = torch.cat(lx, dim=1).sum(axis=1, keepdim=True)
    return torch.sigmoid(self.linear(x)) - self.buff + t

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([ 0.144, -0.375, -0.205], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.012], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Concat(lx_0, lx_1, axis=1) -> cat
  ReduceSum(cat, init7_s1_1, keepdims=1) -> sum_1
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub
    Add(sub, sum_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='lx_0' type=dtype('float32') shape=['batch', 1]
input: name='lx_1' type=dtype('float32') shape=['batch', 2]
init: name='b_buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)-- DynamoInterpret.placeholder.0
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([0.325, 0.316, 0.199], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.523], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Concat(lx_0, lx_1, axis=1) -> cat
  ReduceSum(cat, init7_s1_1, keepdims=1) -> sum_1
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Sub(sigmoid, b_buff) -> sub_4
    Add(sub_4, sum_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 1]

custom-tracing

FAILED

Type is unknown for result 'l', known_types={'x': 1}
--DEBUG--
[GraphBuilder-BNK] Message starts, there are 0 initializers, 0 nodes, 2 inputs, 2 outputs.
--PARAMETERS--
dynamic_examples=
--SHAPE--
dynamic_examples=
dynamic_objects=
   batch = 'batch'
dynamic_objects_rev=
   'batch' = <class 'list'>
     tuple
       'batch'
       ERR**: <class 'torch.SymInt'>:'batch'
dynamic_dimensions_source={'batch': [{'axis': 0, 'input_name': 'x'},
           {'axis': 0, 'input_name': ('lx', 0)},
           {'axis': 0, 'input_name': ('lx', 1)}]}
dynamic_dimensions_source_flat=['x', ('lx', 0), ('lx', 1)]
output_dynamic_dimensions_source_flat=None
dynamic_alias={}
dynamic_shapes={'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>},
        {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}],
 'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}}
_known_types={'x': 1}
_known_shapes={'x': ('batch', 3)}
_known_value_shape={}
_known_constants=[]
_known_ranks={}
--TORCH-USERS--
    cat -> {sum_1}
    lx -> {cat}
    x -> {linear}
--TORCH-SHAPES--
    x: ('run_node', (('example_value', torch.float32, torch.Size([4, 3])), '')) --- 1:2:('batch', 3):
    lx: ('run_node', ('', '')) --- :::
    cat: ('run_node', ('', '')) --- :::
--ONNX--
-- EXEPATH --
export-export_options=ExportOptions(tracing=True)
-- process.graph_module --
graph():
    %x : [num_users=1] = placeholder[target=x]
    %lx : list [num_users=1] = placeholder[target=lx]
    %cat : [num_users=1] = call_function[target=torch.cat](args = (%lx, 1), kwargs = {})
    %sum_1 : [num_users=1] = call_method[target=sum](args = (%cat,), kwargs = {axis: 1, keepdim: True})
    %linear : [num_users=1] = call_module[target=linear](args = (%x,), kwargs = {})
    %sigmoid : [num_users=1] = call_function[target=torch.sigmoid](args = (%linear,), kwargs = {})
    %buff : [num_users=1] = get_attr[target=buff]
    %sub : [num_users=1] = call_function[target=operator.sub](args = (%sigmoid, %buff), kwargs = {})
    %add : [num_users=1] = call_function[target=operator.add](args = (%sub, %sum_1), kwargs = {})
    return add
-- process.progress --
node 2/10 target=<built-in method cat of type object at 0x7fd5086f6ec0>
--
[GraphBuilder-BNK.make_tensor_input] x[1:batchx3]
[GraphBuilder-BNK.make_tensor_input] lx[0:]
[GraphBuilder-BNK] Message completed, there are 0 initializers, 0 nodes, 2 inputs, 2 outputs..

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3]
input: name='lx_0' type=dtype('float32') shape=['s0', 1]
input: name='lx_1' type=dtype('float32') shape=['s0', 2]
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.535,  0.118, -0.217], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.441], dtype=float32)
init: name='buff' type=float32 shape=(1,) -- array([0.5], dtype=float32)
Concat(lx_0, lx_1, axis=1) -> cat
Constant(value=[1]) -> val_3
  ReduceSum(cat, val_3, noop_with_empty_axes=0, keepdims=1) -> sum_1
Gemm(x, linear.weight, linear.bias, beta=1.00, transB=1, alpha=1.00, transA=0) -> linear
  Sigmoid(linear) -> sigmoid
    Sub(sigmoid, buff) -> sub_4
    Add(sub_4, sum_1) -> add_15
output: name='add_15' type=dtype('float32') shape=['s0', 1]

script

FAILED

unable to convert dynamic shapes {'x': {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, 'lx': [{0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}, {0: <class 'experimental_experiment.torch_interpreter.eval.model_cases.batch'>}]}

SignatureShapeAsIndex

forward

def forward(self, x, y):
    t = torch.sigmoid(self.linear(x)) + x
    return t[:, : y.shape[1]]

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 'length']
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.352,  0.054, -0.048], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.006], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Add(sigmoid, x) -> add
Shape(y, end=2, start=1) -> _shape_y0
  Slice(add, init7_s1_0, _shape_y0, init7_s1_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'length']

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 'length']
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.407,  0.566, -0.414], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([0.451], dtype=float32)-- DynamoInterpret.placeholder.1/P(linear.bias)
Reshape(linear.weight, init7_s2_-1_1) -> _onx_transpose_p_linear_weight0
  Reshape(_onx_transpose_p_linear_weight0, init7_s2_1_-1) -> GemmTransposePattern--_onx_transpose_p_linear_weight0
    Gemm(x, GemmTransposePattern--_onx_transpose_p_linear_weight0, linear.bias, transB=1) -> linear
      Sigmoid(linear) -> sigmoid
        Add(sigmoid, x) -> add_6
Shape(y, end=2, start=1) -> _shape_y0
  Slice(add_6, init7_s1_0, _shape_y0, init7_s1_1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 'length']

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 'length']
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.3  , -0.224,  0.249], dtype=float32)-- GraphBuilder.make_nodes/fromlinear.weight##DynamoInterpret.get_attr.1/P(linear.weight)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.205], dtype=float32)-- GraphBuilder.make_nodes/fromlinear.bias##DynamoInterpret.get_attr.1/P(linear.bias)
init: name='init7_s1_1' type=int64 shape=(1,) -- array([1])           -- Opset.make_node.1/Shape
init: name='init7_s1_0' type=int64 shape=(1,) -- array([0])           -- Opset.make_node.1/Shape##Opset.make_node.1/Shape
init: name='getitem_1_axis' type=int64 shape=(2,) -- array([0, 1])    -- DynamoInterpreter._getitem_slice.axis.1
init: name='getitem_1_start' type=int64 shape=(2,) -- array([0, 0])   -- DynamoInterpreter._getitem_slice.2
init: name='getitem_1_step' type=int64 shape=(2,) -- array([1, 1])    -- DynamoInterpreter._getitem_slice.3
init: name='init7_s2_-1_1' type=int64 shape=(2,) -- array([-1,  1])   -- TransposeEqualReshapePattern.apply.new_shape
init: name='init7_s2_1_-1' type=int64 shape=(2,) -- array([ 1, -1])   -- TransposeEqualReshapePattern.apply.new_shape
Reshape(linear.weight, init7_s2_-1_1) -> _sub_Linear__onx_transpose_weight0
  Reshape(_sub_Linear__onx_transpose_weight0, init7_s2_1_-1) -> GemmTransposePattern--_sub_Linear__onx_transpose_weight0
    Gemm(x, GemmTransposePattern--_sub_Linear__onx_transpose_weight0, linear.bias, transB=1) -> _sub_Linear_linear
      Sigmoid(_sub_Linear_linear) -> sigmoid
        Add(sigmoid, x) -> add
          Shape(add) -> getitem_1_shape
            GatherElements(getitem_1_shape, init7_s1_0) -> getitem_1_end
Shape(y) -> getattr_1
  Gather(getattr_1, init7_s1_1) -> _onx_gather_getattr_10
    Concat(getitem_1_end, _onx_gather_getattr_10, axis=0) -> _onx_concat_getitem_1_end0
      Slice(add, getitem_1_start, _onx_concat_getitem_1_end0, getitem_1_axis, getitem_1_step) -> output
output: name='output' type=dtype('float32') shape=['d_output_0', 'd_output_1']

dynamo-ir

opset: domain='pkg.onnxscript.torch_lib.common' version=1
opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['s0', 3]
input: name='y' type=dtype('float32') shape=['s0', 's2']
init: name='linear.weight' type=float32 shape=(1, 3) -- array([-0.145, -0.372, -0.4  ], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.025], dtype=float32)
Constant(value_ints=[-1]) -> val_17
Shape(y, end=2, start=1) -> val_0
  Squeeze(val_0) -> sym_size_int_5
  Reshape(sym_size_int_5, val_17, allowzero=0) -> val_18
Gemm(x, linear.weight, linear.bias, beta=1.00, transB=1, alpha=1.00, transA=0) -> linear
  Sigmoid(linear) -> sigmoid
    Add(sigmoid, x) -> add_6
Constant(value=[0]) -> val_15
Constant(value=[1]) -> val_22
Constant(value_ints=[1]) -> val_23
  Slice(add_6, val_15, val_18, val_22, val_23) -> slice_2
output: name='slice_2' type=dtype('float32') shape=['s0', 's2']

script

opset: domain='' version=17
input: name='x' type=dtype('float32') shape=['batch', 3]
input: name='y' type=dtype('float32') shape=['batch', 'length']
init: name='args_3' type=float32 shape=(1, 3) -- array([-0.189,  0.167, -0.302], dtype=float32)
init: name='linear.bias' type=float32 shape=(1,) -- array([-0.572], dtype=float32)
Constant(value=1) -> /Constant_output_0
Gemm(x, args_3, linear.bias, alpha=1.00, beta=1.00, transB=1) -> /linear/Gemm_output_0
  Sigmoid(/linear/Gemm_output_0) -> /Sigmoid_output_0
    Add(/Sigmoid_output_0, x) -> /Add_output_0
Shape(y) -> /Shape_output_0
  Gather(/Shape_output_0, /Constant_output_0, axis=0) -> /Gather_output_0
Constant(value=[1]) -> /Constant_1_output_0
Constant(value=[0]) -> /Constant_2_output_0
Constant(value=[0]) -> /Constant_3_output_0
  Unsqueeze(/Gather_output_0, /Constant_3_output_0) -> /Unsqueeze_output_0
Constant(value=[1]) -> /Constant_4_output_0
  Slice(/Add_output_0, /Constant_2_output_0, /Unsqueeze_output_0, /Constant_1_output_0, /Constant_4_output_0) -> 21
output: name='21' type=dtype('float32') shape=['batch', 'Slice21_dim_1']

TypeBFloat16

forward

def forward(self, x):
    xb = x.to(torch.bfloat16)
    return (xb + xb).to(torch.float32)

custom-fallback

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
Add(x, x) -> add-x
  Cast(add-x, to=16) -> add
    Cast(add, to=1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-dec

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
Add(x, x) -> add-x
  Cast(add-x, to=16) -> add_3
    Cast(add_3, to=1) -> output_0
output: name='output_0' type=dtype('float32') shape=['batch', 4]

custom-tracing

opset: domain='' version=18
input: name='x' type=dtype('float32') shape=['batch', 4]
Add(x, x) -> add-x
  Cast(add-x, to=16) -> add
    Cast(add, to=1) -> output
output: name='output' type=dtype('float32') shape=['batch', 4]

dynamo-ir

FAILED

[ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for Add(14) node with name 'node_Add_1'

script

FAILED

number of input names provided (4) exceeded number of inputs (1)

Summary

case	custom-dec	custom-fallback	custom-tracing	dynamo-ir	script
AtenAsStrided	FAIL	FAIL	FAIL		FAIL
AtenInterpolate					FAIL
AtenNonZero					FAIL
AtenNonZeroTuple					FAIL
AtenRollPos					FAIL
AtenRollRelu					FAIL
BuildInIsInstance			FAIL		FAIL
BuildInLen			FAIL		FAIL
ComplexPolar	FAIL	FAIL	FAIL		FAIL
ControlFlowCond			FAIL	FAIL	FAIL
ControlFlowCond2Inputs			FAIL	FAIL	FAIL
ControlFlowCond2Outputs			FAIL	FAIL	FAIL
ControlFlowCondConstant			FAIL		FAIL
ControlFlowCondNestedModule			FAIL		FAIL
ControlFlowCondNonZero	FAIL	FAIL	FAIL	FAIL	FAIL
ControlFlowNestCond			FAIL		FAIL
ControlFlowScan			FAIL	FAIL	FAIL
ControlFlowScan2Carried			FAIL	FAIL	FAIL
ControlFlowScanCDist			FAIL	FAIL	FAIL
ControlFlowScanCDist2			FAIL	FAIL	FAIL
ControlFlowScanCDistXY			FAIL	FAIL	FAIL
CreateFromShape			FAIL		FAIL
CreateFromShapeThroughFunction			FAIL		FAIL
CropLastDimensionWithTensorContent	FAIL	FAIL		FAIL	FAIL
CropLastDimensionWithTensorShape					FAIL
InplaceAdd					FAIL
InplaceAdd2			FAIL		FAIL
InplaceAdd_Mul			FAIL		FAIL
InplaceCloneAdd_			FAIL		FAIL
InplaceSetItemEllipsis_1	FAIL	FAIL	FAIL	FAIL	FAIL
InplaceSetItemEllipsis_2	FAIL	FAIL	FAIL	FAIL	FAIL
InplaceSetItemMask			FAIL		FAIL
InplaceSetItemSquare			FAIL		FAIL
InplaceSetItemSquareAdd			FAIL		FAIL
InplaceSetItemSquareAdd2			FAIL		FAIL
SignatureFloat1			FAIL	FAIL	FAIL
SignatureInt1			FAIL	FAIL	FAIL
SignatureInt2	FAIL	FAIL	FAIL	FAIL	FAIL
SignatureListFixedLength					FAIL
SignatureListFixedWithNone	FAIL	FAIL	FAIL	FAIL	FAIL
SignatureListVariableLength			FAIL		FAIL
SignatureShapeAsIndex
TypeBFloat16				FAIL	FAIL