onnx-diagnostic 0.6.0__py3-none-any.whl → 0.6.1__py3-none-any.whl

onnx_diagnostic/torch_onnx/runtime_info.py

@@ -0,0 +1,289 @@
+import enum
+from typing import Any, Dict, List, Optional, Set, Tuple, Union
+import onnx
+import torch
+from ..api import TensorLike
+from ..helpers import string_type
+
+
+class RuntimeValueKind(enum.IntEnum):
+    "Kind of result."
+
+    RESULT = 1
+    INITIALIZER = 3
+    INPUT = 5
+    OUTPUT = 9
+
+    def to_str(self) -> str:
+        for k, v in self.__class__.__dict__.items():
+            if v == int(self):
+                return k
+        raise RuntimeError(f"Unable to display {self!r}")
+
+
+class RuntimeDevice(enum.IntEnum):
+    "Device definition"
+
+    UNKNOWN = 0
+    NEW = 1
+    CPU = 2
+    CUDA = 4
+
+    def to_str(self) -> str:
+        for k, v in self.__class__.__dict__.items():
+            if v == int(self):
+                return k
+        raise RuntimeError(f"Unable to display {self!r}")
+
+
+class RuntimeValue:
+    """Describes a value used during the execution of a model."""
+
+    def __init__(
+        self,
+        name: str,
+        dtype: Optional[Any] = None,
+        shape: Optional[Tuple[Union[str, int], ...]] = None,
+        value: Optional[Any] = None,
+        first_used: Optional[int] = None,
+        last_used: Optional[int] = None,
+        created: Optional[int] = None,
+        is_shape: Optional[bool] = None,
+        kind: Optional[RuntimeValueKind] = None,
+        device: Optional[RuntimeDevice] = None,
+    ):
+        self.name = name
+        self.dtype = dtype
+        self.shape = shape
+        self.value = value
+        self.first_used = first_used
+        self.last_used = last_used
+        self.created = created
+        self.is_shape = is_shape
+        self.kind = kind
+        self.device = device
+
+    def __repr__(self) -> str:
+        "usual"
+        ad = {}
+        for att in [
+            "name",
+            "dtype",
+            "shape",
+            "first_used",
+            "last_used",
+            "is_shape",
+            "kind",
+            "created",
+            "device",
+        ]:
+            v = getattr(self, att)
+            if v is not None:
+                ad[att] = v
+        if self.value is not None:
+            ad["value"] = (
+                self.value.string_type()
+                if hasattr(self.value, "string_type")
+                else string_type(self.value, with_shape=True)
+            )
+        msg = ", ".join(
+            f"{name}={t.to_str()}" if hasattr(t, "to_str") else f"{name}={t}"
+            for name, t in ad.items()
+        )
+        return f"{self.__class__.__name__}({msg})"
+
+    @property
+    def has_value(self) -> bool:
+        "Tells if value is specified."
+        return self.value is not None
+
+    def string_type(self) -> str:
+        "Returns a string describing the value."
+        rows = []
+        if self.shape is not None:
+            rows.append(f"shape={self.shape}")
+        if self.is_shape is not None:
+            rows.append(f"is_shape={self.is_shape}")
+        if self.device is not None:
+            rows.append(f"device={self.device}")
+        text = f", {', '.join(rows)}" if rows else ""
+        if self.value is None:
+            return (
+                f"RuntimeValue(name={self.name!r}{text}"
+                f", dtype={self.dtype}, kind={self.kind})"
+            )
+        return (
+            f"RuntimeValue(name={self.name!r}, "
+            f"kind={self.kind}{text}, value={self.value.string_type()})"
+        )
+
+    def set_value(self, value: Union[torch.Tensor, TensorLike]):
+        """Sets the value."""
+        assert value is not None, "Use clean_value to set a value to None"
+        self.value = value
+        is_sequence = hasattr(value, "is_sequence") and value.is_sequence()
+        if self.dtype:
+            assert value is None or self.dtype == value.dtype, (
+                f"Unexpected dtype={value.dtype}, previous dtype was {self.dtype}, "
+                f"is_sequence={is_sequence}"
+            )
+        else:
+            self.dtype = value.dtype
+        self.shape = None if is_sequence else tuple(map(int, value.shape))
+
+    def clean_value(self):
+        """Sets value to None."""
+        self.value = None
+
+    @property
+    def is_output(self) -> bool:
+        "Tells if it is an output."
+        return self.kind == RuntimeValueKind.OUTPUT
+
+    @property
+    def is_input(self) -> bool:
+        "Tells if it is an input."
+        return self.kind == RuntimeValueKind.INPUT
+
+    @property
+    def is_initializer(self) -> bool:
+        "Tells if it is an initializer."
+        return self.kind == RuntimeValueKind.INITIALIZER
+
+
+def get_hidden_inputs(graph: onnx.GraphProto) -> Set[str]:
+    """
+    Returns the hidden inputs (inputs coming from an upper context)
+    used by a subgraph.
+    """
+    hidden = set()
+    memo = (
+        set(i.name for i in graph.initializer)
+        | set(i.name for i in graph.sparse_initializer)
+        | set(i.name for i in graph.input)
+    )
+    for node in graph.node:
+        for i in node.input:
+            if i not in memo:
+                hidden.add(i)
+        for att in node.attribute:
+            if att.type == onnx.AttributeProto.GRAPH and att.g:
+                hid = get_hidden_inputs(att.g)
+                less = set(h for h in hid if h not in memo)
+                hidden |= less
+        memo |= set(node.output)
+    return hidden
+
+
+def set_is_shape(
+    node: onnx.NodeProto, values: Dict[str, RuntimeValue], drop: Optional[Set[str]] = None
+) -> List[str]:
+    """
+    Sets attribute ``is_shape`` for outputs of a node.
+
+    :param node: node to process
+    :param values: stored results, values in this dictionary are updated
+    :param drop: variables not to consider because the come from the graph
+        holding this subgraph
+    :return: list of modified results
+    """
+    if not node.input:
+        # Constant
+        return []
+    drop = drop or set()
+    if node.op_type in ("Shape", "Size") and node.domain == "":
+        values[node.output[0]].is_shape = True
+        return [node.output[0]]
+    is_shapes = [values[i].is_shape for i in node.input if i not in drop]
+    if any(is_shapes):
+        if is_shapes[0] and len(node.output) == 1:
+            values[node.output[0]].is_shape = True
+            return [node.output[0]]
+    else:
+        for o in node.output:
+            values[o].is_shape = False
+        return list(node.output)
+    return []
+
+
+def first_used_last_used(
+    proto: Union[onnx.FunctionProto, onnx.GraphProto, onnx.ModelProto],
+    constant_as_initializer: bool = False,
+) -> Dict[str, RuntimeValue]:
+    """
+    Builds first used, last used information for every result
+    in the model.
+
+    :param proto: model, graph or function
+    :param constant_as_initializer: outputs of node Constant is tagged as INITIALIZER
+    :return: dictionary of RuntimeValue
+    """
+    values = {}
+    if isinstance(proto, onnx.ModelProto):
+        initializer = proto.graph.initializer
+        sparse_initializer = proto.graph.sparse_initializer
+        _input = proto.graph.input
+        output = proto.graph.output
+        _node = proto.graph.node
+        allow_unknown = False
+    elif isinstance(proto, onnx.GraphProto):
+        initializer = proto.initializer
+        sparse_initializer = proto.sparse_initializer
+        _input = proto.input
+        output = proto.output
+        _node = proto.node
+        allow_unknown = True
+    else:
+        initializer = []
+        sparse_initializer = []
+        _input = proto.input
+        output = proto.output
+        _node = proto.node
+        allow_unknown = False
+
+    for init in initializer:
+        values[init.name] = RuntimeValue(
+            init.name, kind=RuntimeValueKind.INITIALIZER, created=-1
+        )
+    for init in sparse_initializer:
+        values[init.name] = RuntimeValue(
+            init.name, created=-1, kind=RuntimeValueKind.INITIALIZER
+        )
+    for inp in _input:
+        n = inp if isinstance(inp, str) else inp.name
+        values[n] = RuntimeValue(n, created=-1, kind=RuntimeValueKind.INPUT)
+    drop = set()
+    for it, node in enumerate(_node):
+        for i in node.input:
+            if i not in values:
+                assert allow_unknown, f"Input {i!r} is unknown."
+                # This input comes from a context and the model is a GraphProto
+                drop.add(i)
+                continue
+            if values[i].first_used is None:
+                values[i].first_used = it
+            values[i].last_used = it
+        for att in node.attribute:
+            if att.type == onnx.AttributeProto.GRAPH:
+                for n in get_hidden_inputs(att.g):
+                    if values[n].first_used is None:
+                        values[n].first_used = it
+                    values[n].last_used = it
+        is_constant = node.op_type == "Constant" and node.domain == ""
+        for o in node.output:
+            values[o] = RuntimeValue(
+                o,
+                created=it,
+                kind=(
+                    RuntimeValueKind.INITIALIZER
+                    if is_constant and constant_as_initializer
+                    else RuntimeValueKind.RESULT
+                ),
+            )
+        set_is_shape(node, values, drop=drop)
+
+    for out in output:
+        n = out if isinstance(out, str) else out.name
+        values[n].kind = RuntimeValueKind.OUTPUT
+        values[n].last_used = len(_node)
+    return values

{onnx_diagnostic-0.6.0.dist-info → onnx_diagnostic-0.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx-diagnostic
-Version: 0.6.0
+Version: 0.6.1
 Summary: Investigate ONNX models
 Home-page: https://github.com/sdpython/onnx-diagnostic
 Author: Xavier Dupré

{onnx_diagnostic-0.6.0.dist-info → onnx_diagnostic-0.6.1.dist-info}/RECORD

@@ -1,29 +1,31 @@
-onnx_diagnostic/__init__.py,sha256=5S8PigU8f0RN8fU9ddmGimcrAr1kUtpUORdZRi96mHw,173
+onnx_diagnostic/__init__.py,sha256=yCtQh931_2K3SHqvkJ_EVFSKxjtdNDc21rdCxdemDBM,173
 onnx_diagnostic/__main__.py,sha256=YmyV_Aq_ianDlHyKLHMa6h8YK3ZmFPpLVHLKjM91aCk,79
-onnx_diagnostic/_command_lines_parser.py,sha256=yy4upYkizwu-8M6ErGKhzwiX5fW8dWT_34EBOT7CPPQ,18632
+onnx_diagnostic/_command_lines_parser.py,sha256=WSoopSHjXWEgFvzyfGe3_c-hZoStuQPQc_k08siFuf4,19211
+onnx_diagnostic/api.py,sha256=BhCl_yCd78N7TlVtPOHjeYv1QBEy39TjZ647rcHqLh0,345
 onnx_diagnostic/doc.py,sha256=MTuT7Kxyvn7KEy84liQeFeqhugJrUQhjjpx21F72Uxw,926
-onnx_diagnostic/ext_test_case.py,sha256=PVkneWhs-jt_nkfH06hv12WjtaBX0Rim1r_dxGPXjq0,42256
+onnx_diagnostic/ext_test_case.py,sha256=nhWz75caudvKn-svH1ppUY8uw8MoTD4cEdqMdj6PiPc,42399
 onnx_diagnostic/export/__init__.py,sha256=yEIoWiOeTwBsDhyYt2fTKuhtA0Ya1J9u9ZzMTOTWaWs,101
 onnx_diagnostic/export/dynamic_shapes.py,sha256=EHB7VoWNx8sVetvOgE1vgC7wHtIjWDLjanhbEJNpK88,39892
 onnx_diagnostic/export/validate.py,sha256=_PGUql2DJhIgGKo0WjTGUc5AgsZUx8fEs00MePy-w98,6043
 onnx_diagnostic/helpers/__init__.py,sha256=GJ2GT7cgnlIveVUwMZhuvUwidbTJaKv8CsSIOpZDsJg,83
-onnx_diagnostic/helpers/args_helper.py,sha256=7pTrw1A1wuNvLdXJdpda5spPI140FylwSmxxZTGu_4E,4389
+onnx_diagnostic/helpers/args_helper.py,sha256=SRWnqC7EENg09RZlA50B_PcdiIhdbgA4C3ACfzl5nMs,4419
 onnx_diagnostic/helpers/bench_run.py,sha256=CGA6VMJZMH2gDhVueT9ypNm4PMcjGrrGFYp08nhWj9k,16539
 onnx_diagnostic/helpers/cache_helper.py,sha256=soKjyIXa7EQgALd9PAUGIKYzXlJGoLevYiQDsxoqkQ4,8349
 onnx_diagnostic/helpers/config_helper.py,sha256=aZATKVbZuw8L56KQpwMNcqJ3Qi5OplzS_N3ETR3hmj0,3351
 onnx_diagnostic/helpers/graph_helper.py,sha256=hevQT5a7_QuriVPQcbT5qe18n99Doyl5h3-qshx1-uk,14093
-onnx_diagnostic/helpers/helper.py,sha256=h7nuAUWBvLgOq95AY9xIer4rcXhLxkAM1-u-QliAx5A,56929
+onnx_diagnostic/helpers/helper.py,sha256=oPybQruFcVLqvqLDhjphOZ8zZU1HHJWAlABMuTkAO8A,57090
 onnx_diagnostic/helpers/memory_peak.py,sha256=OT6mz0muBbBZY0pjgW2_eCk_lOtFRo-5w4jFo2Z6Kok,6380
 onnx_diagnostic/helpers/mini_onnx_builder.py,sha256=R1Vu4zHzN7GIUnbMVQzpkaXj8cCyyOweWOI9-TSgAHM,20966
-onnx_diagnostic/helpers/model_builder_helper.py,sha256=wHd2qqfGNvdgjGBmXyyZhfikjyM_-ijPkLbMRkqW0Pg,12963
+onnx_diagnostic/helpers/model_builder_helper.py,sha256=cQuC7wbl8UcU_IaSBnX_CsydKTABN6lABCWEthmpmDA,13386
 onnx_diagnostic/helpers/onnx_helper.py,sha256=chw-HB4iqGCD_16d0_BaCnreEgWYW4KeH78nh-3t2Uw,29213
 onnx_diagnostic/helpers/ort_session.py,sha256=UgUUeUslDxEFBc6w6f3HMq_a7bn4TBlItmojqWquSj4,29281
-onnx_diagnostic/helpers/rt_helper.py,sha256=PbMRp0AQGKxj9B8_-oIMYPG5o86jTXJalkoBTmg4VZs,4147
-onnx_diagnostic/helpers/torch_helper.py,sha256=83HnFGcOX8YmPDAikhxFpBydxfI3gyWPDiRHYidrH6A,31531
-onnx_diagnostic/reference/__init__.py,sha256=0Al5kins8LlBICAsszEZ59thMwmaARBO6fMwtYpKOOQ,98
+onnx_diagnostic/helpers/rt_helper.py,sha256=BXU_u1syk2RyM0HTFHKEiO6rHHhZW2UFPyUTVdeq8BU,4251
+onnx_diagnostic/helpers/torch_helper.py,sha256=mrmn4mBeRvMRJ9cEu7BbNG-AHq2OJfSm8dxgtzh-yQQ,31631
+onnx_diagnostic/reference/__init__.py,sha256=nrd09rRuwMDBCPTSZ6kSKZXp1W9W_ExO1t9duDlBnh8,146
 onnx_diagnostic/reference/evaluator.py,sha256=RzNzjFDeMe-4X51Tb22N6aagazY5ktNq-mRmPcfY5EU,8848
 onnx_diagnostic/reference/ort_evaluator.py,sha256=OaWMREF8fuJwimmONpIjQ6WxQT1X2roDsdJsgR8H_Cg,24853
 onnx_diagnostic/reference/quantized_tensor.py,sha256=5u67uS2uGacdMD5VYCbpojNjiesDlV_kO0fAJ0vUWGE,1098
+onnx_diagnostic/reference/torch_evaluator.py,sha256=uvcpDROoCDd8Rln_kieNRfraNg9j1FD39n1xiGNh3LA,20825
 onnx_diagnostic/reference/ops/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 onnx_diagnostic/reference/ops/op_add_add_mul_mul.py,sha256=CXQVtgVrT066gDJFwxL4nDSY4G8r08XNu3EwhWqMapU,1521
 onnx_diagnostic/reference/ops/op_attention.py,sha256=ThALMDF53v3QeG1bohi0bvX2o90HZhGJbbAFOtwEHPE,2027
@@ -53,11 +55,23 @@ onnx_diagnostic/reference/ops/op_skip_layer_normalization.py,sha256=oJ7fQNx2iQh9
 onnx_diagnostic/reference/ops/op_slice.py,sha256=yRxfYBs8b7QezyyG9JHCD8MIJHij2qR2NNDpBmD3FJI,705
 onnx_diagnostic/reference/ops/op_transpose_cast.py,sha256=ifef74rvh0Yvq1Zx51B4mfnISbxV9uRg9DFjkdL1_68,361
 onnx_diagnostic/reference/ops/op_tri_matrix.py,sha256=Yn2gxAyygcwtF5Hjau9ihXDAzul0BAkdqVimVahtFBU,519
-onnx_diagnostic/tasks/__init__.py,sha256=b7AquEcM1Pdjp-m9K-z83_dOpvyXf4NWXNuzrl1Qxfg,1648
+onnx_diagnostic/reference/torch_ops/__init__.py,sha256=DzuCaiKbzJnkXprJVbVJwA7A29w6T_W1_plB_ZXDQsk,1144
+onnx_diagnostic/reference/torch_ops/_op_run.py,sha256=1nnW6Ub3jWkS-HI3--dhYNXRLqy9Ppe7F9kOeGGYRhw,10253
+onnx_diagnostic/reference/torch_ops/access_ops.py,sha256=sLiTbZUfNbATQxVpq2Rv8n6cbV4jJmQlWHUVIds_GlY,3102
+onnx_diagnostic/reference/torch_ops/binary_ops.py,sha256=774QlWFPvNtNhwxtLb-d28jhTO8U0cthoJKHjM89WrA,2641
+onnx_diagnostic/reference/torch_ops/controlflow_ops.py,sha256=EsiMFmLHxFHprCSz9OLlYxo3sMaF9czj-4NOFkHZH5c,4362
+onnx_diagnostic/reference/torch_ops/generator_ops.py,sha256=oxoeg7YxQiEaC20qOFI-BwQuBtkxN7y9XD9o3gPjPkI,871
+onnx_diagnostic/reference/torch_ops/nn_ops.py,sha256=wzXuBfMsA1aQPQDi4qAv0oZ8kB1qwt4reQ8LiWg1ulo,6906
+onnx_diagnostic/reference/torch_ops/other_ops.py,sha256=bIZsyqrRfTI1xiC4WvV5LcQawsy4gqqci9EgOO9rk9c,3766
+onnx_diagnostic/reference/torch_ops/reduce_ops.py,sha256=oeA-NNJ1MFQD7xG5RD61_3SQhXvpJpNXKZ-_0rFikjE,5020
+onnx_diagnostic/reference/torch_ops/sequence_ops.py,sha256=q1bwFI1zUO69KrOOAbNFqBhz1s9YkqxV1kCaBmgIoYI,2215
+onnx_diagnostic/reference/torch_ops/shape_ops.py,sha256=1pR-3EwhuMpAE-B2TUJs83GxDGITaLBHKxExJ-Ie1EE,4095
+onnx_diagnostic/reference/torch_ops/unary_ops.py,sha256=T3EtQW0p_kNN-OhjVsk1STZ0uWxXyB-rYO-lIp3gXuU,1630
+onnx_diagnostic/tasks/__init__.py,sha256=5XXM-rv-Hk2gSHvqsww9DzVd9mcRifacgcPgvPCjnDM,2412
 onnx_diagnostic/tasks/automatic_speech_recognition.py,sha256=oRoYy56M0Yv_WOcn1hJXv-R9wgHkJ8rbym7j7y8oslw,6851
 onnx_diagnostic/tasks/feature_extraction.py,sha256=V-T5NpZ6EimOz00weWWxGfksZ9jQ5ZQyaP-mxuCEuJo,2223
 onnx_diagnostic/tasks/fill_mask.py,sha256=POUtgvOWv8wTOVLqxPNsj_C2WBiBWkmM72Z9mNlNqxI,2341
-onnx_diagnostic/tasks/image_classification.py,sha256=qgT9tbXby3dACZyXXjvfpm0a7-ey2-vxMCXtjoDusJw,4210
+onnx_diagnostic/tasks/image_classification.py,sha256=wtSkZB6Wqh2Y1O_zjfnYRZxUQPVVUlLQ_4D0H-SG-xU,4140
 onnx_diagnostic/tasks/image_text_to_text.py,sha256=6rKbts_p05VZL8wufJa6NP-MhxUOU-fuTAks5QfUVVQ,6037
 onnx_diagnostic/tasks/mixture_of_expert.py,sha256=orMx8Ly4DO0Po0tEmme4gi2flPIGip4TaAyxVik4Zgg,2685
 onnx_diagnostic/tasks/object_detection.py,sha256=o1T8NMztjdFAFA-Z5efx-8nd9W7YZZcbE8Ag5wKVxZA,3930
@@ -65,7 +79,7 @@ onnx_diagnostic/tasks/sentence_similarity.py,sha256=okQ-TQR8j1a92_N-eT6xN56rjtu2
 onnx_diagnostic/tasks/summarization.py,sha256=qK9E7TdaB9g_Mu-f4Vdr_X8mMAUSlIapLlc8FlWSGFU,7989
 onnx_diagnostic/tasks/text2text_generation.py,sha256=x5p_5n72scF9hFNOVP8BjOr4Lga1nnqtjfStZ_n9EwQ,8406
 onnx_diagnostic/tasks/text_classification.py,sha256=OgC_G9iumzTjTNUEvMoFFNTHCD8_BkdvdYC4jUsfpHM,2412
-onnx_diagnostic/tasks/text_generation.py,sha256=Wv8DamBHte355wXe_tAeVxG4EL20y86fu7JEmUM75to,10385
+onnx_diagnostic/tasks/text_generation.py,sha256=jWKBFt7M-Neyjw6YSOrYY28xOkRkIerDF5YlugKK3qk,10386
 onnx_diagnostic/tasks/zero_shot_image_classification.py,sha256=N3cEG1Lq95wS1N_CWUUUCU5j-4Tp5eR8Ce68U8THYAk,4380
 onnx_diagnostic/torch_export_patches/__init__.py,sha256=0SaZedwznm1hQUCvXZsGZORV5vby954wEExr5faepGg,720
 onnx_diagnostic/torch_export_patches/onnx_export_errors.py,sha256=MgOQwgLf6-uCGQaiUrhVNfZQ43dCp1iWGbzLbKEVyc8,18810
@@ -73,27 +87,28 @@ onnx_diagnostic/torch_export_patches/onnx_export_serialization.py,sha256=l5HvE_F
 onnx_diagnostic/torch_export_patches/patch_expressions.py,sha256=vr4tt61cbDnaaaduzMj4UBZ8OUtr6GfDpIWwOYqjWzs,3213
 onnx_diagnostic/torch_export_patches/patch_inputs.py,sha256=9b4pmyT00BwLqi7WG-gliep1RUy3gXEgW6BDnlSSA-M,7689
 onnx_diagnostic/torch_export_patches/patch_module.py,sha256=R2d9IHM-RwsBKDsxuBIJnEqMoxbS9gd4YWFGG2wwV5A,39881
-onnx_diagnostic/torch_export_patches/patch_module_helper.py,sha256=-sFpuBnwPl61Y0KKENniMfQkL-0-3SaLn5mzgF-fP6g,1946
-onnx_diagnostic/torch_export_patches/eval/__init__.py,sha256=V8gbjsbYJHyjLo4WyzhsDx-noBQn6bsK1lhgm8IQlzQ,20890
-onnx_diagnostic/torch_export_patches/eval/model_cases.py,sha256=KtK4AgrFE2Mm8wo15O7x4deTGubOU9MFp3QCuac6WkM,26471
+onnx_diagnostic/torch_export_patches/patch_module_helper.py,sha256=sIvu4E9BsCB8f-KlM4xykR19mflDfLGaiel6nb9ZGx8,6926
+onnx_diagnostic/torch_export_patches/eval/__init__.py,sha256=VtkQB1o3Q2Fh99OOF6vQ2dynkhwzx2Wx6oB-rRbvTI0,23954
+onnx_diagnostic/torch_export_patches/eval/model_cases.py,sha256=DTvdHPtNQh25Akv5o3D4Jxf1L1-SJ7w14tgvj8AAns8,26577
 onnx_diagnostic/torch_export_patches/patches/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnx_diagnostic/torch_export_patches/patches/patch_torch.py,sha256=KaZ8TjDa9ATgT4HllYzzoNf_51q_yOj_GuF5NYjPCrU,18913
-onnx_diagnostic/torch_export_patches/patches/patch_transformers.py,sha256=QGuZ_j8juG9dlSUBSpc2T1nYwkoeFz3iP2kONx2Hmrc,23025
+onnx_diagnostic/torch_export_patches/patches/patch_transformers.py,sha256=Hf-U50vzgzJ4iUjS2LAYkbfmzCEwX80Dzvdrr-Rhlp0,26456
 onnx_diagnostic/torch_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnx_diagnostic/torch_models/llms.py,sha256=soyg4yC87ptGoeulJhKqw5opGmuLvH1pn_ZDXZ4Jr8E,90
-onnx_diagnostic/torch_models/test_helper.py,sha256=SU8HwQtfUEicCpukp_prqX0ol5fu2rA06lc1GROxW38,55309
+onnx_diagnostic/torch_models/test_helper.py,sha256=72HE_fY0m9TNly1w_b2dD-P67eSLJreOMYtT6W6CLfQ,58704
 onnx_diagnostic/torch_models/hghub/__init__.py,sha256=vi1Q7YHdddj1soiBN42MSvJdFqe2_KUoWafHISjwOu8,58
 onnx_diagnostic/torch_models/hghub/hub_api.py,sha256=BgM_p57Q0gT9GOhdrmOYcnbuTTzCWp80jS4OQqWwFhs,9990
 onnx_diagnostic/torch_models/hghub/hub_data.py,sha256=885wKyZkdM-Qp5Sg6C9Ol1dxigmA8FYAko-Ys08sppo,8096
-onnx_diagnostic/torch_models/hghub/hub_data_cached_configs.py,sha256=gndvVH_OybEAQaaG4ZvqFELrZaEozTeHDpdW2AK9m9M,255155
+onnx_diagnostic/torch_models/hghub/hub_data_cached_configs.py,sha256=V4Wv_73QsiWMFTw-xqj-5yZOri1NKuAub6VQa2UVIpw,259582
 onnx_diagnostic/torch_models/hghub/model_inputs.py,sha256=1h1jHJknqDHAa308_bjOzXVPgy3GIF-ikpce8CHNTmE,7804
 onnx_diagnostic/torch_models/untrained/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnx_diagnostic/torch_models/untrained/llm_phi2.py,sha256=ynBTDHJHCk44NjLT_t6OiFDBdPP0rFGPteiONDxvztw,3708
 onnx_diagnostic/torch_models/untrained/llm_tiny_llm.py,sha256=7N3fGvT_4Mn4NbIo0Qk57c6DMc3OXGWyvj_P41rjwSY,3513
 onnx_diagnostic/torch_onnx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+onnx_diagnostic/torch_onnx/runtime_info.py,sha256=1g9F_Jf9AAgYQU4stbsrFXwQl-30mWlQrFbQ7val8Ps,9268
 onnx_diagnostic/torch_onnx/sbs.py,sha256=1EL25DeYFzlBSiFG_XjePBLvsiItRXbdDrr5-QZW2mA,16878
-onnx_diagnostic-0.6.0.dist-info/licenses/LICENSE.txt,sha256=Vv6TXglX6Rc0d-f8aREhayhT-6PMQXEyOmI2NKlUCMc,1045
-onnx_diagnostic-0.6.0.dist-info/METADATA,sha256=jqrQEqFmrlycVGKW_zlSrxhzMoeV-X-H4eSeGBZyK1o,6643
-onnx_diagnostic-0.6.0.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-onnx_diagnostic-0.6.0.dist-info/top_level.txt,sha256=KwNkXewmcobM3ZT1DJLVWH6ebJzA5qKg7cWqKfpGNT4,16
-onnx_diagnostic-0.6.0.dist-info/RECORD,,
+onnx_diagnostic-0.6.1.dist-info/licenses/LICENSE.txt,sha256=Vv6TXglX6Rc0d-f8aREhayhT-6PMQXEyOmI2NKlUCMc,1045
+onnx_diagnostic-0.6.1.dist-info/METADATA,sha256=j0i2pgpY_6bD7IFlqqdmIZSVSvv67Q-7X4N4fih-2JQ,6643
+onnx_diagnostic-0.6.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+onnx_diagnostic-0.6.1.dist-info/top_level.txt,sha256=KwNkXewmcobM3ZT1DJLVWH6ebJzA5qKg7cWqKfpGNT4,16
+onnx_diagnostic-0.6.1.dist-info/RECORD,,

{onnx_diagnostic-0.6.0.dist-info → onnx_diagnostic-0.6.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.8.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any