onnx-diagnostic 0.8.3__py3-none-any.whl → 0.8.5__py3-none-any.whl

onnx_diagnostic/torch_models/validate.py

@@ -349,13 +349,15 @@ def _prepare_validation(
     verbose,
     output_names,
     dump_folder,
+    submodule,
 ):
     main_validation_begin = time.perf_counter()
-    model_id, subfolder, same_as_pretrained, use_pretrained = _preprocess_model_id(
+    model_id, subfolder, same_as_pretrained, use_pretrained, submodule = _preprocess_model_id(
         model_id,
         subfolder,
         same_as_pretrained=same_as_pretrained,
         use_pretrained=use_pretrained,
+        submodule=submodule,
     )
     time_preprocess_model_id = time.perf_counter() - main_validation_begin
     patch_kwargs = make_patch_kwargs(patch=patch, rewrite=rewrite)
@@ -364,6 +366,7 @@ def _prepare_validation(
     summary.update(
         dict(
             version_model_id=model_id,
+            version_submodule=submodule,
             version_do_run=str(do_run),
             version_dtype=str(dtype or ""),
             version_device=str(device or ""),
@@ -444,6 +447,7 @@ def _prepare_validation(
         dump_folder,
         folder_name,
         patch_kwargs,
+        submodule,
     )
 
 
@@ -460,6 +464,7 @@ def _get_untrained_model_with_inputs(
     inputs2,
     quiet,
     dump_folder,
+    submodule,
 ):
     iop = input_options or {}
     mop = model_options or {}
@@ -480,6 +485,7 @@ def _get_untrained_model_with_inputs(
                     model_kwargs=mop,
                     subfolder=sub,
                     add_second_input=i2,
+                    submodule=submodule,
                 )
             )
         ),
@@ -842,6 +848,7 @@ def validate_model(
     ort_logs: bool = False,
     quiet_input_sets: Optional[Set[str]] = None,
     save_ep: Optional[str] = None,
+    submodule: Optional[str] = None,
 ) -> Tuple[Dict[str, Union[int, float, str]], Dict[str, Any]]:
     """
     Validates a model.
@@ -902,6 +909,7 @@ def validate_model(
         even if quiet is False
     :param save_ep: if not empty, this can be used to save the input sets and
         the exported program
+    :param submodule: to test not the model but a submodule of this model
     :return: two dictionaries, one with some metrics,
         another one with whatever the function produces
 
@@ -966,6 +974,7 @@ def validate_model(
         use_pretrained=use_pretrained,
         same_as_pretrained=same_as_pretrained,
         save_ep=save_ep,
+        submodule=submodule,
     )
     if dump_folder:
         with open(dump_stats, "w") as f:
@@ -1053,6 +1062,7 @@ def _validate_model_step1(
     use_pretrained,
     same_as_pretrained,
     save_ep,
+    submodule,
 ):
     assert not do_same or do_run, (
         f"Discrepancies cannot be measured if the model is not run, "
@@ -1067,6 +1077,7 @@ def _validate_model_step1(
         dump_folder,
         folder_name,
         patch_kwargs,
+        submodule,
     ) = _prepare_validation(
         model_id=model_id,
         subfolder=subfolder,
@@ -1093,6 +1104,7 @@ def _validate_model_step1(
         verbose=verbose,
         output_names=output_names,
         dump_folder=dump_folder,
+        submodule=submodule,
     )
 
     data, iop, mop = _get_untrained_model_with_inputs(
@@ -1108,6 +1120,7 @@ def _validate_model_step1(
         inputs2=inputs2,
         quiet=quiet,
         dump_folder=dump_folder,
+        submodule=submodule,
     )
 
     second_input_keys = [k for k in data if k.startswith("inputs") and k != "inputs"]

onnx_diagnostic/torch_onnx/runtime_info.py

@@ -4,6 +4,7 @@ import onnx
 import torch
 from ..api import TensorLike
 from ..helpers import string_type
+from ..helpers.onnx_helper import get_hidden_inputs
 
 
 class RuntimeValueKind(enum.IntEnum):
@@ -151,30 +152,6 @@ class RuntimeValue:
         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]:

onnx_diagnostic/torch_onnx/sbs.py

@@ -7,7 +7,12 @@ import numpy as np
 import torch
 from ..helpers import string_type, string_diff, max_diff, flatten_object
 from ..helpers.onnx_helper import pretty_onnx
-from ..helpers.torch_helper import to_numpy, from_numpy, to_tensor, torch_dtype_to_onnx_dtype
+from ..helpers.torch_helper import (
+    to_numpy,
+    from_numpy,
+    to_tensor,
+    torch_dtype_to_onnx_dtype,
+)
 from ..helpers.torch_fx_graph_helper import prepare_args_kwargs, run_fx_node
 from ..reference.ort_evaluator import OnnxList, OnnxruntimeEvaluator
 from .sbs_dataclasses import (
@@ -381,7 +386,8 @@ def _preparation_with_fx_graph(
                 assert len(torch_input_names) < len(onx.graph.input), (
                     f"torch_input_names={torch_input_names!r}, "
                     f"onnx_input_names={[n.name for n in onx.graph.input]}, "
-                    f"node.name={node.name!r} cannot be an input"
+                    f"node.name={node.name!r} cannot be an input, "
+                    f"placeholders_to_state_dict={sorted(placeholders_to_state_dict)}"
                 )
                 assert node.name not in skip_mapping_torch_onnx, (
                     f"{node.name!r} is ambiguous, cannot be mapped due to "
@@ -772,9 +778,9 @@ def run_aligned(
     # preparation with ep.graph.nodes
     ep_state_dict = {**ep.state_dict, **dict(ep.named_buffers(), **ep.tensor_constants)}
     placeholders_to_state_dict = {
-        **{f"p_{name.replace('.', '_')}": name for name in ep.state_dict},
-        **{f"b_{name.replace('.', '_')}": name for name, _ in ep.named_buffers()},
-        **{f"c_{name.replace('.', '_')}": name for name in ep.tensor_constants},
+        **{f"p_{name.replace('.', '_').lower()}": name for name in ep.state_dict},
+        **{f"b_{name.replace('.', '_').lower()}": name for name, _ in ep.named_buffers()},
+        **{f"c_{name.replace('.', '_').lower()}": name for name in ep.tensor_constants},
     }
     skip_mapping_torch_onnx = _duplicated_values(placeholders_to_state_dict)
     placeholders = {}

onnx_diagnostic/torch_onnx/sbs_dataclasses.py

@@ -11,7 +11,12 @@ except ImportError:
 import onnx
 import numpy as np
 import torch
-from ..helpers.onnx_helper import extract_subset_of_nodes, make_submodel, from_array_extended
+from ..helpers.onnx_helper import (
+    extract_subset_of_nodes,
+    make_submodel,
+    from_array_extended,
+    select_model_inputs_outputs,
+)
 from ..helpers.torch_helper import torch_dtype_to_onnx_dtype
 
 
@@ -61,12 +66,16 @@ class ReplayConfiguration:
     :param selected_names: list of results names to dump
     :param selected_op_types: list of onnx operators to dump
     :param threshold: only keep those whose discrepancies is greater than that threshold
+    :param dump_prefix_model: after dumping the smallest model able to replicate
+        one given output, if also dumps the models producing the inputs
+        and the outputs truncated from the big one
     """
 
     dump_folder: str
     selected_names: Optional[Set[str]] = None
     selected_op_types: Optional[Set[str]] = None
     threshold: float = 0.1
+    dump_prefix_model: bool = False
 
     def __post_init__(self):
         assert self.dump_folder, "dump_folder is empty and this is not allowed for the replay"
@@ -243,7 +252,17 @@ class ReplayConfiguration:
         :return: the folder created to dump everything
         """
         if verbose:
-            print(f"[ReplayConfiguration.dump] extract subset of node for {name!r}")
+            print(
+                f"[ReplayConfiguration.dump] extract subset of nodes for "
+                f"{name!r} (onnx_id_node={onnx_id_node})"
+            )
+            if verbose >= 10:
+                print(f"[ReplayConfiguration.dump] onnx_results={sorted(onnx_results)}")
+                print(f"[ReplayConfiguration.dump] torch_results={sorted(torch_results)}")
+                print(
+                    f"[ReplayConfiguration.dump] onnx_name_to_ep_name="
+                    f"{sorted(onnx_name_to_ep_name)}"
+                )
         nodes = extract_subset_of_nodes(
             model=model,
             name=name,
@@ -253,7 +272,8 @@ class ReplayConfiguration:
         if not nodes:
             if verbose:
                 print(
-                    f"[ReplayConfiguration.dump] could not extract subset of node for {name!r}"
+                    f"[ReplayConfiguration.dump] could not extract subset of "
+                    f"nodes for {name!r}"
                 )
             return None
         if verbose:
@@ -286,7 +306,7 @@ class ReplayConfiguration:
             del submodel.graph.input[:]
             submodel.graph.input.extend(new_inputs)
             if verbose:
-                print(f"[ReplayConfiguration.dump] removed input {removed_inputs}")
+                print(f"[ReplayConfiguration.dump] removed inputs {removed_inputs}")
                 print(f"[ReplayConfiguration.dump] final model inputs {input_names}")
 
         onnx.save(submodel, os.path.join(folder, "model.onnx"))
@@ -307,6 +327,30 @@ class ReplayConfiguration:
         )
         with open(os.path.join(folder, "replay.py"), "w") as f:
             f.write(self.get_replay_code())
+
+        if self.dump_prefix_model:
+            main_inputs = {
+                i.name: onnx_inputs.get(i.name, torch_inputs.get(i.name, None))
+                for i in model.graph.input
+            }
+            # only saving onnx inputs, torch should be the same
+            torch.save(main_inputs, os.path.join(folder, "onnx_main_inputs.pt"))
+
+            model_inputs_file = os.path.join(folder, "model.inputs.onnx")
+            exclude = {i.name for i in model.graph.input} | {
+                i.name for i in model.graph.initializer
+            }
+            model_inputs = select_model_inputs_outputs(
+                model, outputs=[i.name for i in submodel.graph.input if i.name not in exclude]
+            )
+            onnx.save(model_inputs, model_inputs_file)
+
+            model_outputs_file = os.path.join(folder, "model.outputs.onnx")
+            model_outputs = select_model_inputs_outputs(
+                model, outputs=[i.name for i in submodel.graph.output]
+            )
+            onnx.save(model_outputs, model_outputs_file)
+
         if verbose:
             print(f"[ReplayConfiguration.dump] done {folder!r}")
         return folder

{onnx_diagnostic-0.8.3.dist-info → onnx_diagnostic-0.8.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx-diagnostic
-Version: 0.8.3
+Version: 0.8.5
 Summary: Tools to help converting pytorch models into ONNX.
 Home-page: https://github.com/sdpython/onnx-diagnostic
 Author: Xavier Dupré

{onnx_diagnostic-0.8.3.dist-info → onnx_diagnostic-0.8.5.dist-info}/RECORD

@@ -1,16 +1,16 @@
-onnx_diagnostic/__init__.py,sha256=q-JGXWdB5HIHrAPUbiGuZ3aflvcrMyhNffVzOd5xO-8,173
+onnx_diagnostic/__init__.py,sha256=dCiBK_S7EOo_rAsmsgv-laLhtKzE2uny0XIR5aO4eDk,173
 onnx_diagnostic/__main__.py,sha256=YmyV_Aq_ianDlHyKLHMa6h8YK3ZmFPpLVHLKjM91aCk,79
-onnx_diagnostic/_command_lines_parser.py,sha256=KFKyH254F7FdcKKc2QrtAjpGLpLwnduflPvqm3FM0UI,51441
+onnx_diagnostic/_command_lines_parser.py,sha256=ZFJdQP1Ee8D5a_xUch-0CHaYbbILztejTjVdyc9KrMw,52667
 onnx_diagnostic/api.py,sha256=BhCl_yCd78N7TlVtPOHjeYv1QBEy39TjZ647rcHqLh0,345
 onnx_diagnostic/doc.py,sha256=t3RELgfooYnVMAi0JSpggWkQEgUsREz8NmRvn0TnLI8,2829
-onnx_diagnostic/ext_test_case.py,sha256=bA4oK1mnccbt5Ien24I9nhiDgay0IjCxOeH1lPU5E-g,47798
+onnx_diagnostic/ext_test_case.py,sha256=rVZWqFEfnvwnsD3wF4jeDblh5uj5ckZ8C6DZQ0RGb_E,49599
 onnx_diagnostic/export/__init__.py,sha256=yEIoWiOeTwBsDhyYt2fTKuhtA0Ya1J9u9ZzMTOTWaWs,101
-onnx_diagnostic/export/api.py,sha256=xivxtvjFAIbKquAsGLjVp9J_CZl6KWeO8IT4wii9FOI,9649
+onnx_diagnostic/export/api.py,sha256=BX4c99gMlRYsBWk3P15FMRogArxjP4dXYXP5gILjgIk,10626
 onnx_diagnostic/export/control_flow.py,sha256=zU5n_QYhNcBllyMsl1_i6ohZt2CshqG2MokJghrvA60,7751
 onnx_diagnostic/export/control_flow_onnx.py,sha256=sODOD4v7EJj6LWhrfcdCW68r9nYKsRM4SRnqDw4TrSI,18049
-onnx_diagnostic/export/control_flow_research.py,sha256=UMAlriHKBLoYJzdq3kCmsUIKOlYQE0OjFbJ8zkuvuwI,5220
+onnx_diagnostic/export/control_flow_research.py,sha256=RuYz9_eM42Bk6TKSiPV6dS68LIMZu-6WBCFCKoSvjrk,5422
 onnx_diagnostic/export/dynamic_shapes.py,sha256=M2hlpHSTbkzZwGKAbrpQXng5HQrwjF5Z6wGGxEgnp74,42061
-onnx_diagnostic/export/onnx_plug.py,sha256=vwUyOtF5aihAO-98QSmY_sD9w0hNMnGKaSxG0cF0ZCo,14660
+onnx_diagnostic/export/onnx_plug.py,sha256=U13fL0BjnhMzcDGxaAOqM4TQte5Z4zKDg4ESS0iktjM,22704
 onnx_diagnostic/export/shape_helper.py,sha256=m628y0oRCQbeZkeh8JDHIfWMsSjoJoeX-IPiPGDHT-w,11273
 onnx_diagnostic/export/validate.py,sha256=_PGUql2DJhIgGKo0WjTGUc5AgsZUx8fEs00MePy-w98,6043
 onnx_diagnostic/helpers/__init__.py,sha256=GJ2GT7cgnlIveVUwMZhuvUwidbTJaKv8CsSIOpZDsJg,83
@@ -20,22 +20,22 @@ onnx_diagnostic/helpers/bench_run.py,sha256=CGA6VMJZMH2gDhVueT9ypNm4PMcjGrrGFYp0
 onnx_diagnostic/helpers/cache_helper.py,sha256=OLghsSUuZ8cWGkua8eH75KBF-mbVqejnNUYfFo5lRf0,28498
 onnx_diagnostic/helpers/config_helper.py,sha256=cWRETgFhZ7tayIZPnMqF8BF5AvTU64G2BMqyzgO7lzs,5670
 onnx_diagnostic/helpers/doc_helper.py,sha256=pl5MZd3_FaE8BqQnqoBuSBxoNCFcd2OJd3eITUSku5c,5897
-onnx_diagnostic/helpers/dot_helper.py,sha256=Ii6jg-1YUJPI6cPhhTeD8rc5PJR0GIiGa2PLOdWJyA8,7798
+onnx_diagnostic/helpers/dot_helper.py,sha256=hwgTJsbsUv0qq7euyPDnc1NsBZDGOwv32JXSZxIHJkE,8118
 onnx_diagnostic/helpers/fake_tensor_helper.py,sha256=J7wnK3WTuVKnYiMzLVTAPkdJr3hQfIfMC9ZlOu7oGmI,11024
 onnx_diagnostic/helpers/graph_helper.py,sha256=hevQT5a7_QuriVPQcbT5qe18n99Doyl5h3-qshx1-uk,14093
-onnx_diagnostic/helpers/helper.py,sha256=aCPkAU6iNmHA3Glt_uehEiBOIIZtXDgq9hjhdG5Ol3Y,65568
+onnx_diagnostic/helpers/helper.py,sha256=x8EYQmgrz_G5QS_IsbeFIoDcN_sUs-CslJMHseBj1Fw,65482
 onnx_diagnostic/helpers/log_helper.py,sha256=0lJiTF87lliI-LmgpUH_V2N8NuzJ0LryH0mSYpkRaL8,93272
 onnx_diagnostic/helpers/memory_peak.py,sha256=M3m4_thWFIwP5HytbJYEqaijXIv5v5BW_vlcJowIYI4,6434
 onnx_diagnostic/helpers/mini_onnx_builder.py,sha256=jR2lkRZEQ0N30H0FqeBwaxJd_w_6kyxFagrnulqFjhE,23883
 onnx_diagnostic/helpers/model_builder_helper.py,sha256=qKIq4Naqq03gk6NfqXLQjSDiKL5FFNc1AEyVX0R8GmA,18540
-onnx_diagnostic/helpers/onnx_helper.py,sha256=BCf1djXB--eY_FJv9ldD85bQ--OMI_uPDJN6SumdbdM,43057
-onnx_diagnostic/helpers/ort_session.py,sha256=TFCDgcG3Nvj_1S0xTIUqDw0WTSeav0NMJFYCfT_W-dw,30505
+onnx_diagnostic/helpers/onnx_helper.py,sha256=MshvqMSTNUUZIpkkRYGDymdW2t2KtB2BgYtOPHIDwvQ,57508
+onnx_diagnostic/helpers/ort_session.py,sha256=XvRazj7yyepaQwYHpPkKKi9v8u_h9A4ZiFH6IxjqPKs,30502
 onnx_diagnostic/helpers/rt_helper.py,sha256=OOxHSCKZup2u7zTvVJxPkRHb4jQZ03KpkiDGrfwibMM,38135
 onnx_diagnostic/helpers/torch_fx_graph_helper.py,sha256=7xFe4svdbr4gV3OTNcx8eJejjDyHAv4hD_RNNKSxL0c,6571
-onnx_diagnostic/helpers/torch_helper.py,sha256=gtkk31BptY5JvNOvbx_1Bfyuns_mQu9gEO0upoUTdy4,38294
+onnx_diagnostic/helpers/torch_helper.py,sha256=ADV81WWCskQ-jmzn1GI_LU8GqBtufCHS3oeLG-3Uw0E,38954
 onnx_diagnostic/reference/__init__.py,sha256=rLZsxOlnb7-81F2CzepGnZLejaROg4JvgFaGR9FwVQA,208
 onnx_diagnostic/reference/evaluator.py,sha256=RzNzjFDeMe-4X51Tb22N6aagazY5ktNq-mRmPcfY5EU,8848
-onnx_diagnostic/reference/ort_evaluator.py,sha256=RsTboIAL1QqudV6X3P3VxBPxLtJJF8TsxNdyy0L5epE,34773
+onnx_diagnostic/reference/ort_evaluator.py,sha256=q7Dn0yC3LPadlfRnhiRzVn32k9ma_IivdYyhyecgNgc,33930
 onnx_diagnostic/reference/quantized_tensor.py,sha256=5u67uS2uGacdMD5VYCbpojNjiesDlV_kO0fAJ0vUWGE,1098
 onnx_diagnostic/reference/report_results_comparison.py,sha256=OsyQN8EHZZoj97u74RQP-7WFpebPOso5GEDpdkLWu6M,3645
 onnx_diagnostic/reference/torch_evaluator.py,sha256=Tx1teWvfGEX5RmkDnI83UiOlo5eBOC72vPhgTWdFUF0,27689
@@ -110,16 +110,16 @@ onnx_diagnostic/torch_export_patches/patch_module_helper.py,sha256=2U0AdyZuU0W54
 onnx_diagnostic/torch_export_patches/eval/__init__.py,sha256=YQoOGt9XQLWqnJ15NnT7ri_jDevfvpuQwEJo38E-VRU,25056
 onnx_diagnostic/torch_export_patches/eval/model_cases.py,sha256=9h4yo9vKiK-E6zaXyAsxXGM-lCjd88ONybA1F3YcTI4,27988
 onnx_diagnostic/torch_export_patches/patches/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-onnx_diagnostic/torch_export_patches/patches/_patch_transformers_attention.py,sha256=kI0qgAGFxkyvx8wikQtPcik_zpPpTAQypQ1cMQsjetw,7730
+onnx_diagnostic/torch_export_patches/patches/_patch_transformers_attention.py,sha256=5JOyT95BNwHIuxaSFJDSEGsoI-6IwbgNnFwg2q3UM-Q,7731
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_cache_utils.py,sha256=UdxLii-od2OpQmUJbmXmZinXeLBItVFrr75BVT1Y0zw,2041
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_causal_mask.py,sha256=h37DPVxsq8iAWECnTlKW5tVqSBgPBF52xr3uxsjdi2k,3113
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_dynamic_cache.py,sha256=lEdYqX60pyi_w6PrbCTk7NC96nB8FFcFRf_JMjXSAZE,7961
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_gemma3.py,sha256=nVgYQk0xXpHiictN1wOHVMN2lTH9b0vfIJ4ie-uKopg,1999
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_generation_mixin.py,sha256=VIZsVHgR8NmAcBQalPl5I6ZzNgcBxjGb6ars31m9gRg,21936
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_idefics.py,sha256=kTjuTRsfkGGGhspJnMxAMQSchZgGC_IruJzpHh_FmI8,6348
-onnx_diagnostic/torch_export_patches/patches/_patch_transformers_masking_utils.py,sha256=R4YwnN9ktxjjImiJtLRxiKtKLr9LuFlwkPXkTJ6BTIo,6895
+onnx_diagnostic/torch_export_patches/patches/_patch_transformers_masking_utils.py,sha256=HE3fovyvMiYe9EPz1UjdD9AWopX3H188SMwPb8w5mzM,7111
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_qwen2.py,sha256=OxYdlLrwtd_KGHt3E17poduxvWFg-CfGS57-yN1i6gI,3827
-onnx_diagnostic/torch_export_patches/patches/_patch_transformers_qwen2_5.py,sha256=-THcoMvJ1MhLZFQP6c2IEGqpkY7sTg_xYyAwCE7_91o,29511
+onnx_diagnostic/torch_export_patches/patches/_patch_transformers_qwen2_5.py,sha256=GS7IDHyRaLAsbZE5k7KN-ZT5-ezbmEUzXPJ_xG4SulA,31601
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_qwen3.py,sha256=cND9Iqo1aKdlX-BXGr9Qlq_Y4EW1L5VWSwZfqYTVazU,4888
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_rotary_embedding.py,sha256=4bJ_z2gizZQla_fcCVt0dmuhzO9Vu-D7CCMWdxMlrKM,16893
 onnx_diagnostic/torch_export_patches/patches/_patch_transformers_sam_mask_decoder.py,sha256=-6TuBm3sLAFEGuW3vRfOTtE5uP6aINFfu7xMnl27Dws,5703
@@ -130,24 +130,24 @@ onnx_diagnostic/torch_export_patches/serialization/__init__.py,sha256=BHLdRPtNAt
 onnx_diagnostic/torch_export_patches/serialization/diffusers_impl.py,sha256=drq3EH_yjcSuIWYsVeUWm8Cx6YCZFU6bP_1PLtPfY5I,945
 onnx_diagnostic/torch_export_patches/serialization/transformers_impl.py,sha256=sIHFvUQoMK8ytXQYB-k7OL62z8A3f5uDaq-S5R5uN-M,10034
 onnx_diagnostic/torch_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-onnx_diagnostic/torch_models/code_sample.py,sha256=PWf7piGx7Eiv7BOTpL2bLUtWwaVcw7SMBvkSpEzZDPs,12883
+onnx_diagnostic/torch_models/code_sample.py,sha256=rCDZY64pkn6uIbJJSBuC5TlU_-uleI73I9GlbXtJd54,12923
 onnx_diagnostic/torch_models/llms.py,sha256=soyg4yC87ptGoeulJhKqw5opGmuLvH1pn_ZDXZ4Jr8E,90
-onnx_diagnostic/torch_models/validate.py,sha256=yhcCjZJ7pgjeHQBV-rCbQJ-ot_tngEwSYoonyNhEH5g,94426
+onnx_diagnostic/torch_models/validate.py,sha256=fnbTl5v1n5nM2MpmCgCMaWa6c7DGpb5mZYSuHXXCJEs,94829
 onnx_diagnostic/torch_models/hghub/__init__.py,sha256=vi1Q7YHdddj1soiBN42MSvJdFqe2_KUoWafHISjwOu8,58
 onnx_diagnostic/torch_models/hghub/hub_api.py,sha256=rFbiPNLET-KdBpnv-p0nKgwHX6d7C_Z0s9zZ86_92kQ,14307
 onnx_diagnostic/torch_models/hghub/hub_data.py,sha256=8V_pAgACPLPsLRYUododg7MSL6str-T3tBEGY4OaeYQ,8724
 onnx_diagnostic/torch_models/hghub/hub_data_cached_configs.py,sha256=GimzkI8W3guATkDx7RQ-w2xNGVaFDVegfTnnmNxf4iE,292068
-onnx_diagnostic/torch_models/hghub/model_inputs.py,sha256=bVjf7Tm8tTi0dbqQZbcbNXDWuS5g6YBfR3xyeQ-NAWM,16285
+onnx_diagnostic/torch_models/hghub/model_inputs.py,sha256=tCGqigRyY1omxm2rczRUvCTsweZGbF1MccWI3MmCH20,17423
 onnx_diagnostic/torch_models/hghub/model_specific.py,sha256=j50Nu7wddJMoqmD4QzMbNdFDUUgUmSBKRzPDH55TlUQ,2498
 onnx_diagnostic/torch_models/untrained/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnx_diagnostic/torch_models/untrained/llm_phi2.py,sha256=y_akbdApi136qHcEQgykwIAYVw0Yfi0lbjb3DNuafaU,3948
 onnx_diagnostic/torch_models/untrained/llm_tiny_llm.py,sha256=QXw_Bs2SzfeiQMf-tmtVl83SmVOL4-Um7Qy-f0E48QI,2507
 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=Q2nbj1Ovasf_HDFc5_tNVH8taJhzhgUXPY6N1uajayk,40615
-onnx_diagnostic/torch_onnx/sbs_dataclasses.py,sha256=ctJitdW09gLhg900yjT-Zqbx8SU2n4ZdgyVZ47dmlvQ,18475
-onnx_diagnostic-0.8.3.dist-info/licenses/LICENSE.txt,sha256=Vv6TXglX6Rc0d-f8aREhayhT-6PMQXEyOmI2NKlUCMc,1045
-onnx_diagnostic-0.8.3.dist-info/METADATA,sha256=MsLK613cwgCcvJ4JkLvP2ysF48KEgTmzqm83IBUO5JM,6734
-onnx_diagnostic-0.8.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-onnx_diagnostic-0.8.3.dist-info/top_level.txt,sha256=KwNkXewmcobM3ZT1DJLVWH6ebJzA5qKg7cWqKfpGNT4,16
-onnx_diagnostic-0.8.3.dist-info/RECORD,,
+onnx_diagnostic/torch_onnx/runtime_info.py,sha256=u1bD6VXqzBCRmqmbzQtDswaPs1PH_ygr1r-CrcfXpNU,8562
+onnx_diagnostic/torch_onnx/sbs.py,sha256=8okBEIupMgw7TtKc80YFimMtwnY3GchdY05FsA9ooa0,40749
+onnx_diagnostic/torch_onnx/sbs_dataclasses.py,sha256=UctdBjzoPTQG1LS0tZ8A6E9hpoq5HWUYaJLPOPJc9FI,20299
+onnx_diagnostic-0.8.5.dist-info/licenses/LICENSE.txt,sha256=Vv6TXglX6Rc0d-f8aREhayhT-6PMQXEyOmI2NKlUCMc,1045
+onnx_diagnostic-0.8.5.dist-info/METADATA,sha256=A54IonPIcnualwiRJhvjRMfhF3p3jdXhEH1vTtZBgyE,6734
+onnx_diagnostic-0.8.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+onnx_diagnostic-0.8.5.dist-info/top_level.txt,sha256=KwNkXewmcobM3ZT1DJLVWH6ebJzA5qKg7cWqKfpGNT4,16
+onnx_diagnostic-0.8.5.dist-info/RECORD,,