Sample data overhaul

data.py

@@ -77,10 +77,32 @@ def get_distant_data() -> pd.DataFrame:
 
 
 def get_sample_data() -> pd.DataFrame:
-    path = os.path.join(os.path.dirname(__file__), "sample_data.csv")
-    df = pd.read_csv(path)
-    df = df.set_index("model_name")
-    return df
+    # Retrieve sample dataframes
+    df_amd = read_one_dataframe("sample_amd.json", "amd")
+    df_nvidia = read_one_dataframe("sample_nvidia.json", "nvidia")
+    # Join both dataframes
+    joined = df_amd.join(df_nvidia, rsuffix="_nvidia", lsuffix="_amd", how="outer")
+    joined = joined[
+        [
+            "success_amd",
+            "success_nvidia",
+            "failed_multi_no_amd",
+            "failed_multi_no_nvidia",
+            "failed_single_no_amd",
+            "failed_single_no_nvidia",
+            "failures_amd",
+            "failures_nvidia",
+            "job_link_amd",
+            "job_link_nvidia",
+        ]
+    ]
+    joined.index = joined.index.str.replace("^models_", "", regex=True)
+    # Fitler out all but important models
+    important_models_lower = [model.lower() for model in IMPORTANT_MODELS]
+    filtered_joined = joined[joined.index.str.lower().isin(important_models_lower)]
+    # Prefix all model names with "sample_"
+    filtered_joined.index = "sample_" + filtered_joined.index
+    return filtered_joined
 
 def extract_model_data(row: pd.Series) -> tuple[dict[str, int], dict[str, int], int, int, int, int]:
     """Extract and process model data from DataFrame row."""

sample_amd.json

@@ -0,0 +1,1709 @@
+{
+    "models_auto": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 80,
+        "time_spent": "5.47, 1.74, ",
+        "failures": {},
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409911",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410689"
+        }
+    },
+    "models_bert": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 239,
+        "time_spent": "0:02:22, 0:02:16, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4216)  AssertionError: Tensor-likes are not equal!"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4216)  AssertionError: Tensor-likes are not equal!"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409938",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410716"
+        }
+    },
+    "models_clip": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 288,
+        "time_spent": "0:03:29, 0:03:30, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410734",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409965"
+        }
+    },
+    "models_detr": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 77,
+        "time_spent": "0:01:13, 0:01:49, ",
+        "failures": {},
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410020",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410868"
+        }
+    },
+    "models_gemma3": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 12,
+                "multi": 13
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 341,
+        "time_spent": "0:07:52, 0:09:43, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4219)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager",
+                    "trace": "(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_1b_text_only",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['Wri[57 chars]s, a silent stream,\\nInto the neural net, a wa[42 chars],\\n'] != ['Wri[57 chars]s, a river deep,\\nWith patterns hidden, secret[46 chars]ing']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [264 chars]cow\"] != ['use[114 chars]rown and white cow standing on a sandy beach n[272 chars]ach']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [55 chars]ike'] != ['use[114 chars]rown and white cow standing on a sandy beach w[68 chars]oks']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_crops",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[251 chars]. There's a blue sky with some white clouds in the background\"] != [\"use[251 chars]. There's a bright blue sky with some white clouds in the\"]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_multiimage",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[122 chars]n\\n**Main Features:**\\n\\n*   **Chinese Archway[19 chars]ent\"] != [\"use[122 chars]n\\n**Overall Scene:**\\n\\nIt looks like a stree[18 chars]nt,\"]"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4219)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallelism",
+                    "trace": "(line 925)  RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager",
+                    "trace": "(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_1b_text_only",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['Wri[57 chars]s, a silent stream,\\nInto the neural net, a wa[42 chars],\\n'] != ['Wri[57 chars]s, a river deep,\\nWith patterns hidden, secret[46 chars]ing']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [264 chars]cow\"] != ['use[114 chars]rown and white cow standing on a sandy beach n[272 chars]ach']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [55 chars]ike'] != ['use[114 chars]rown and white cow standing on a sandy beach w[68 chars]oks']"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_crops",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[251 chars]. There's a blue sky with some white clouds in the background\"] != [\"use[251 chars]. There's a bright blue sky with some white clouds in the\"]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_multiimage",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[122 chars]n\\n**Main Features:**\\n\\n*   **Chinese Archway[19 chars]ent\"] != [\"use[122 chars]n\\n**Overall Scene:**\\n\\nIt looks like a stree[18 chars]nt,\"]"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410076",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410943"
+        }
+    },
+    "models_gemma3n": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 0,
+        "time_spent": ".56, .97, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410944",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410122"
+        }
+    },
+    "models_got_ocr2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 146,
+        "time_spent": "0:01:56, 0:01:39, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410969",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410123"
+        }
+    },
+    "models_gpt2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 249,
+        "time_spent": "0:04:53, 0:02:05, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410990",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410088"
+        }
+    },
+    "models_internvl": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 252,
+        "time_spent": "0:02:54, 0:02:55, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward",
+                    "trace": "(line 727)  AssertionError: False is not true : Actual logits: tensor([ -9.8750,  -0.4885,   1.4668, -10.3359, -10.3359], dtype=torch.float16)"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward",
+                    "trace": "(line 727)  AssertionError: False is not true : Actual logits: tensor([ -9.8750,  -0.4885,   1.4668, -10.3359, -10.3359], dtype=torch.float16)"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527411014",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410165"
+        }
+    },
+    "models_llama": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 232,
+        "time_spent": "0:10:51, 0:23:47, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527411041",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410199"
+        }
+    },
+    "models_llava": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 4,
+                "multi": 5
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 202,
+        "time_spent": "0:02:38, 0:02:51, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
+                    "trace": "(line 399)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
+                    "trace": "(line 399)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527411134",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410218"
+        }
+    },
+    "models_mistral3": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 198,
+        "time_spent": "0:14:37, 0:05:43, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_generate",
+                    "trace": "(line 715)  AssertionError: 'The [14 chars] two cats lying on a pink surface, which appea[21 chars] bed' != 'The [14 chars] two tabby cats lying on a pink surface, which[23 chars]n or'"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_generate",
+                    "trace": "(line 715)  AssertionError: 'The [14 chars] two cats lying on a pink surface, which appea[21 chars] bed' != 'The [14 chars] two tabby cats lying on a pink surface, which[23 chars]n or'"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409417",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410265"
+        }
+    },
+    "models_modernbert": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 5,
+                "multi": 5
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 132,
+        "time_spent": "0:02:22, 0:01:49, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm",
+                    "trace": "(line 401)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head",
+                    "trace": "(line 423)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification",
+                    "trace": "(line 469)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification",
+                    "trace": "(line 446)  AssertionError: Tensor-likes are not close!"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm",
+                    "trace": "(line 401)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head",
+                    "trace": "(line 423)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification",
+                    "trace": "(line 469)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification",
+                    "trace": "(line 446)  AssertionError: Tensor-likes are not close!"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410294",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409446"
+        }
+    },
+    "models_qwen2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 214,
+        "time_spent": "0:02:23, 0:02:39, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410392",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409572"
+        }
+    },
+    "models_qwen2_5_omni": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 167,
+        "time_spent": "0:06:59, 0:02:55, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism",
+                    "trace": "(line 715)  AssertionError: Items in the second set but not the first:"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.\"] != [\"sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.\"]"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
+                    "trace": "(line 715)  AssertionError: Lists differ: [\"sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.\"] != [\"sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.\"]"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410407",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409568"
+        }
+    },
+    "models_qwen2_5_vl": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 204,
+        "time_spent": "0:03:59, 0:03:58, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 406)  AssertionError: Tensor-likes are not equal!"
+                },
+                {
+                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
+                    "trace": "(line 715)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410397",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409587"
+        }
+    },
+    "models_smolvlm": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 323,
+        "time_spent": "0:02:49, 0:02:35, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409653",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410495"
+        }
+    },
+    "models_t5": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 3,
+                "multi": 4
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 254,
+        "time_spent": "0:05:05, 0:03:30, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
+                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
+                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test",
+                    "trace": "(line 727)  AssertionError: False is not true"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410524",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409705"
+        }
+    },
+    "models_vit": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 135,
+        "time_spent": "0:02:19, 0:01:21, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410589",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409755"
+        }
+    },
+    "models_wav2vec2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 0,
+        "time_spent": "0.96, .03, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410594",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409797"
+        }
+    },
+    "models_whisper": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 0,
+        "time_spent": ".19, .20, ",
+        "failures": {},
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527409794",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460430974/job/46527410606"
+        }
+    }
+}

sample_data.csv

@@ -1,22 +0,0 @@
-model_name,success_amd,success_nvidia,failed_multi_no_amd,failed_multi_no_nvidia,failed_single_no_amd,failed_single_no_nvidia,failures_amd,failures_nvidia,job_link_amd,job_link_nvidia
-sample_auto,80,226,0,0,0,0,{},{},"{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501262', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500785'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561673', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561472'}"
-sample_bert,239,527,2,2,2,2,"{'multi': [{'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4201)  AssertionError: Tensor-likes are not equal!'}], 'single': [{'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4201)  AssertionError: Tensor-likes are not equal!'}]}","{'single': [{'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4216)  AssertionError: Tensor-likes are not equal!'}], 'multi': [{'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4216)  AssertionError: Tensor-likes are not equal!'}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501282', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500788'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561709', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561482'}"
-sample_clip,288,660,0,0,0,0,{},{},"{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500866', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501323'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561994', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562125'}"
-sample_detr,69,177,4,0,4,0,"{'multi': [{'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_no_head', 'trace': '(line 595)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_object_detection_head', 'trace': '(line 619)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_panoptic_segmentation_head', 'trace': '(line 667)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTests::test_inference_no_head', 'trace': '(line 741)  AssertionError: Tensor-likes are not close!'}], 'single': [{'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_no_head', 'trace': '(line 595)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_object_detection_head', 'trace': '(line 619)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTestsTimmBackbone::test_inference_panoptic_segmentation_head', 'trace': '(line 667)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/detr/test_modeling_detr.py::DetrModelIntegrationTests::test_inference_no_head', 'trace': '(line 741)  AssertionError: Tensor-likes are not close!'}]}",{},"{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501397', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500969'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562517', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562397'}"
-sample_gemma3,349,499,8,8,7,7,"{'single': [{'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[374 chars]t scenes:\\n\\n*   **Image 1** shows a cow on a beach.\\n'] != ['use[374 chars]t scenes. \\n\\n*   **Image 1** shows a cow standing on a beach']""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[251 chars]. The sky is blue with some white clouds. It’s[405 chars]h a'] != ['use[251 chars]. There are clouds in the blue sky above.', 'u[398 chars]h a']""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[154 chars]each next to a turquoise ocean. There are some[16 chars]lue'] != ['use[154 chars]each with turquoise water and a distant coastl[28 chars]oks']""}], 'multi': [{'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4204)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[374 chars]t scenes:\\n\\n*   **Image 1** shows a cow on a beach.\\n'] != ['use[374 chars]t scenes. \\n\\n*   **Image 1** shows a cow standing on a beach']""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[251 chars]. The sky is blue with some white clouds. It’s[405 chars]h a'] != ['use[251 chars]. There are clouds in the blue sky above.', 'u[398 chars]h a']""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16', 'trace': ""(line 675)  AssertionError: Lists differ: ['use[154 chars]each next to a turquoise ocean. There are some[16 chars]lue'] != ['use[154 chars]each with turquoise water and a distant coastl[28 chars]oks']""}]}","{'single': [{'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4216)  AssertionError: Tensor-likes are not equal!'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache', 'trace': ""(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa', 'trace': '(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager', 'trace': '(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops', 'trace': '(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]'}], 'multi': [{'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4219)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallelism', 'trace': '(line 925)  RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache', 'trace': ""(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')""}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa', 'trace': '(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager', 'trace': '(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3'}, {'line': 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops', 'trace': '(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]'}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501046', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501545'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563053', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562857'}"
-sample_gemma3n,0,286,0,2,0,1,{},"{'multi': [{'line': 'tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}], 'single': [{'line': 'tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501047', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501538'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562955', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563061'}"
-sample_got_ocr2,145,254,2,2,2,1,"{'multi': [{'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}], 'single': [{'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}]}","{'multi': [{'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}], 'single': [{'line': 'tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501556', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501063'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562995', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563212'}"
-sample_gpt2,249,487,1,1,1,1,"{'single': [{'line': 'tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}], 'multi': [{'line': 'tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}]}","{'multi': [{'line': 'tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}], 'single': [{'line': 'tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501087', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501566'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563001', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563255'}"
-sample_internvl,249,356,4,3,4,2,"{'single': [{'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward', 'trace': '(line 687)  AssertionError: False is not true : Actual logits: tensor([ -9.8828,  -0.5005,   1.4697, -10.3438, -10.3438], dtype=torch.float16)'}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_interleaved_images_videos', 'trace': ""(line 675)  AssertionError: 'user[118 chars]nse. Upon closer inspection, the differences b[31 chars]. **' != 'user[118 chars]nse. After re-examining the images, I can see [13 chars]e no'""}], 'multi': [{'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward', 'trace': '(line 687)  AssertionError: False is not true : Actual logits: tensor([ -9.8828,  -0.5005,   1.4697, -10.3438, -10.3438], dtype=torch.float16)'}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_interleaved_images_videos', 'trace': ""(line 675)  AssertionError: 'user[118 chars]nse. Upon closer inspection, the differences b[31 chars]. **' != 'user[118 chars]nse. After re-examining the images, I can see [13 chars]e no'""}]}","{'multi': [{'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads', 'trace': '(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help.'}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}], 'single': [{'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads', 'trace': '(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help.'}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501143', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501636'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563553', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563712'}"
-sample_llama,229,478,4,2,4,1,"{'multi': [{'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_torch_compile_for_training', 'trace': '(line 951)  AssertionError: expected size 2==2, stride 20==64 at dim=0; expected size 2==2, stride 10==32 at dim=1; expected size 10==32, stride 1==1 at dim=2'}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16', 'trace': '(line 687)  AssertionError: False is not true'}], 'single': [{'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_torch_compile_for_training', 'trace': '(line 951)  AssertionError: expected size 2==2, stride 20==64 at dim=0; expected size 2==2, stride 10==32 at dim=1; expected size 10==32, stride 1==1 at dim=2'}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16', 'trace': '(line 687)  AssertionError: False is not true'}]}","{'multi': [{'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}], 'single': [{'line': 'tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501675', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501165'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563871', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564103'}"
-sample_llava,201,346,5,4,4,3,"{'single': [{'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads', 'trace': '(line 687)  AssertionError: False is not true'}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation', 'trace': '(line 548)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes'}], 'multi': [{'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads', 'trace': '(line 687)  AssertionError: False is not true'}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4182)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1'}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation', 'trace': '(line 548)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes'}]}","{'multi': [{'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads', 'trace': '(line 687)  AssertionError: False is not true'}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1'}], 'single': [{'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads', 'trace': '(line 687)  AssertionError: False is not true'}, {'line': 'tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids', 'trace': '(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1'}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501186', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447501727'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564002', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564108'}"
-sample_mistral3,197,286,3,2,3,1,"{'multi': [{'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_batched_generate', 'trace': '(line 675)  AssertionError: \'Calm waters reflect\\nWooden path to distant shore\\nSilence in the scene\' != ""Wooden path to calm,\\nReflections whisper secrets,\\nNature\'s peace unfolds.""'}], 'single': [{'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_batched_generate', 'trace': '(line 675)  AssertionError: \'Calm waters reflect\\nWooden path to distant shore\\nSilence in the scene\' != ""Wooden path to calm,\\nReflections whisper secrets,\\nNature\'s peace unfolds.""'}]}","{'single': [{'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}], 'multi': [{'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500305', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447499780'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561480', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561618'}"
-sample_modernbert,132,164,5,5,5,5,"{'single': [{'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export', 'trace': ""(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']""}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm', 'trace': '(line 401)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head', 'trace': '(line 423)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification', 'trace': '(line 469)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification', 'trace': '(line 446)  AssertionError: Tensor-likes are not close!'}], 'multi': [{'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export', 'trace': ""(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']""}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm', 'trace': '(line 401)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head', 'trace': '(line 423)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification', 'trace': '(line 469)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification', 'trace': '(line 446)  AssertionError: Tensor-likes are not close!'}]}","{'multi': [{'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export', 'trace': ""(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']""}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm', 'trace': '(line 401)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head', 'trace': '(line 423)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification', 'trace': '(line 469)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification', 'trace': '(line 446)  AssertionError: Tensor-likes are not close!'}], 'single': [{'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export', 'trace': ""(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']""}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm', 'trace': '(line 401)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head', 'trace': '(line 423)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification', 'trace': '(line 469)  AssertionError: Tensor-likes are not close!'}, {'line': 'tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification', 'trace': '(line 446)  AssertionError: Tensor-likes are not close!'}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447499811', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500326'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561668', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561515'}"
-sample_qwen2,213,438,3,3,3,2,"{'multi': [{'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache', 'trace': ""(line 1638)  torch._dynamo.exc.TorchRuntimeError: Failed running call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,""}], 'single': [{'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_generate_compilation_all_outputs', 'trace': ""(line 317)  torch._dynamo.exc.Unsupported: isinstance(NestedUserFunctionVariable(), TorchInGraphFunctionVariable(<class 'torch.nn.parameter.Parameter'>)): can't determine type of NestedUserFunctionVariable()""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache', 'trace': ""(line 1638)  torch._dynamo.exc.TorchRuntimeError: Failed running call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,""}]}","{'multi': [{'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache', 'trace': ""(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,""}], 'single': [{'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache', 'trace': ""(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500458', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447499989'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562376', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562270'}"
-sample_qwen2_5_omni,168,277,2,5,1,1,"{'single': [{'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch', 'trace': '(line 675)  AssertionError: Lists differ: [""sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.""] != [""sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.""]'}], 'multi': [{'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism', 'trace': '(line 675)  AssertionError: Items in the second set but not the first:'}, {'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch', 'trace': '(line 675)  AssertionError: Lists differ: [""sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.""] != [""sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.""]'}]}","{'multi': [{'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism', 'trace': '(line 675)  AssertionError: Items in the second set but not the first:'}, {'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}, {'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch', 'trace': '(line 675)  AssertionError: Lists differ: [""sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.""] != [""sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.""]'}, {'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_multiturn', 'trace': '(line 849)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 1 has a total capacity of 22.18 GiB of which 6.50 MiB is free. Process 51940 has 22.17 GiB memory in use. Of the allocated memory 21.74 GiB is allocated by PyTorch, and 27.83 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)'}, {'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_w_audio', 'trace': '(line 1000)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 1 has a total capacity of 22.18 GiB of which 8.50 MiB is free. Process 51940 has 22.17 GiB memory in use. Of the allocated memory 21.75 GiB is allocated by PyTorch, and 17.78 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)'}], 'single': [{'line': 'tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch', 'trace': '(line 675)  AssertionError: Lists differ: [""sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.""] != [""sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.""]'}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447499993', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500491'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562375', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562289'}"
-sample_qwen2_5_vl,204,311,1,1,2,1,"{'single': [{'line': 'tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test', 'trace': ""(line 700)  requests.exceptions.ConnectionError: HTTPSConnectionPool(host='qianwen-res.oss-accelerate-overseas.aliyuncs.com', port=443): Max retries exceeded with url: /Qwen2-VL/demo_small.jpg (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7b289312aad0>: Failed to establish a new connection: [Errno -2] Name or service not known'))""}, {'line': 'tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions', 'trace': ""(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']""}], 'multi': [{'line': 'tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions', 'trace': ""(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']""}]}","{'multi': [{'line': 'tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions', 'trace': ""(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']""}], 'single': [{'line': 'tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions', 'trace': ""(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']""}]}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447499984', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500447'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562382', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562290'}"
-sample_smolvlm,323,499,1,1,1,1,"{'multi': [{'line': 'tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}], 'single': [{'line': 'tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}]}","{'single': [{'line': 'tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}], 'multi': [{'line': 'tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500533', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500052'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562675', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562798'}"
-sample_t5,254,592,4,3,3,2,"{'multi': [{'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 130)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization', 'trace': ""(line 885)  torch._dynamo.exc.TorchRuntimeError: Failed running call_function <built-in function add>(*(FakeTensor(..., size=(1, 8, 1, 1234)), FakeTensor(..., device='cuda:1', size=(1, 1, 1, 1234))), **{}):""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test', 'trace': '(line 687)  AssertionError: False is not true'}], 'single': [{'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4125)  KeyError: 'eager'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization', 'trace': ""(line 885)  torch._dynamo.exc.TorchRuntimeError: Failed running call_function <built-in function add>(*(FakeTensor(..., size=(1, 8, 1, 1234)), FakeTensor(..., device='cuda:0', size=(1, 1, 1, 1234))), **{}):""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test', 'trace': '(line 687)  AssertionError: False is not true'}]}","{'multi': [{'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization', 'trace': ""(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'""}], 'single': [{'line': 'tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization', 'trace': ""(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500560', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500103'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563047', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562939'}"
-sample_vit,135,217,0,0,0,0,{},{},"{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500654', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500177'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563537', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563397'}"
-sample_wav2vec2,0,672,0,4,0,4,{},"{'multi': [{'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool', 'trace': '(line 675)  AssertionError: Traceback (most recent call last):'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}], 'single': [{'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool', 'trace': '(line 675)  AssertionError: Traceback (most recent call last):'}, {'line': 'tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool', 'trace': '(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py'}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500676', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500194'}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563711', 'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563582'}"
-sample_whisper,0,1010,0,11,0,8,{},"{'single': [{'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!\'] != ["" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!\']'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[422 chars]to a fisher shows in lip-nitsky attack that cu[7903 chars]le!""] != ["" Fo[422 chars]to a Fisher shows in lip-nitsky attack that cu[7918 chars]le.""]'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.""] != ["" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.""]'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}], 'multi': [{'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'""}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_forced_decoder_ids', 'trace': '(line 713)  requests.exceptions.ReadTimeout: (ReadTimeoutError(""HTTPSConnectionPool(host=\'huggingface.co\', port=443): Read timed out. (read timeout=10)""), \'(Request ID: 13cb0b08-c261-4ca3-a58f-91a2f3e327ed)\')'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation', 'trace': '(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!\'] != ["" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!\']'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[422 chars]to a fisher shows in lip-nitsky attack that cu[7903 chars]le!""] != ["" Fo[422 chars]to a Fisher shows in lip-nitsky attack that cu[7918 chars]le.""]'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond', 'trace': '(line 675)  AssertionError: Lists differ: ["" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.""] != ["" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.""]'}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_eager_padding_matches_padding_free_with_position_ids', 'trace': ""(line 4140)  KeyError: 'eager'""}, {'line': 'tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_multi_gpu_data_parallel_forward', 'trace': ""(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'""}]}","{'multi': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500690', 'single': 'https://github.com/huggingface/transformers/actions/runs/16433423306/job/46447500204'}","{'single': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563737', 'multi': 'https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563862'}"

sample_nvidia.json

@@ -0,0 +1,1776 @@
+{
+    "models_auto": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 226,
+        "time_spent": "4.66, 6.10, ",
+        "failures": {},
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561673",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561472"
+        }
+    },
+    "models_bert": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 527,
+        "time_spent": "0:01:58, 0:02:00, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4216)  AssertionError: Tensor-likes are not equal!"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/bert/test_modeling_bert.py::BertModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4216)  AssertionError: Tensor-likes are not equal!"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561709",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561482"
+        }
+    },
+    "models_clip": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 660,
+        "time_spent": "0:02:24, 0:02:20, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561994",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562125"
+        }
+    },
+    "models_detr": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 177,
+        "time_spent": "0:01:14, 0:01:19, ",
+        "failures": {},
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562517",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562397"
+        }
+    },
+    "models_gemma3": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 7,
+                "multi": 8
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 499,
+        "time_spent": "0:07:50, 0:07:52, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4216)  AssertionError: Tensor-likes are not equal!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager",
+                    "trace": "(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3ModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4219)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallelism",
+                    "trace": "(line 925)  RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_export_text_only_with_hybrid_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_function <built-in function scaled_dot_product_attention>(*(FakeTensor(..., size=(1, 4, 1, 256), grad_fn=<AddBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>), FakeTensor(..., size=(1, 4, 4096, 256), grad_fn=<CloneBackward0>)), **{'attn_mask': FakeTensor(..., size=(1, 1, 1, 512), dtype=torch.bool), 'dropout_p': 0.0, 'scale': 0.0625, 'is_causal': False}): got RuntimeError('Attempting to broadcast a dimension of length 512 at -1! Mismatching argument at index 1 had torch.Size([1, 1, 1, 512]); but expected shape should be broadcastable to [1, 4, 1, 4096]')"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_1_sdpa",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (4826) must match the existing size (4807) at non-singleton dimension 3.  Target sizes: [2, 4, 4807, 4826].  Tensor sizes: [2, 1, 4807, 4807]"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_generation_beyond_sliding_window_2_eager",
+                    "trace": "(line 265)  RuntimeError: The size of tensor a (4826) must match the size of tensor b (4807) at non-singleton dimension 3"
+                },
+                {
+                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
+                    "trace": "(line 81)  RuntimeError: The expanded size of the tensor (1646) must match the existing size (1617) at non-singleton dimension 3.  Target sizes: [2, 8, 1617, 1646].  Tensor sizes: [2, 1, 1617, 1617]"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563053",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562857"
+        }
+    },
+    "models_gemma3n": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 286,
+        "time_spent": "0:02:29, 0:02:32, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562955",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563061"
+        }
+    },
+    "models_got_ocr2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 254,
+        "time_spent": "0:02:02, 0:02:15, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/got_ocr2/test_modeling_got_ocr2.py::GotOcr2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562995",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563212"
+        }
+    },
+    "models_gpt2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 487,
+        "time_spent": "0:02:23, 0:02:38, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563001",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563255"
+        }
+    },
+    "models_internvl": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 356,
+        "time_spent": "0:05:48, 0:04:49, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help."
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help."
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563553",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563712"
+        }
+    },
+    "models_llama": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 478,
+        "time_spent": "0:04:05, 0:03:53, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563871",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564103"
+        }
+    },
+    "models_llava": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 3,
+                "multi": 4
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 346,
+        "time_spent": "0:10:11, 0:09:28, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 687)  AssertionError: False is not true"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_flex_attention_with_grads",
+                    "trace": "(line 687)  AssertionError: False is not true"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4197)  IndexError: The shape of the mask [3, 23] at index 1 does not match the shape of the indexed tensor [3, 3, 8, 8] at index 1"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564002",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526564108"
+        }
+    },
+    "models_mistral3": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 2
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 286,
+        "time_spent": "0:10:06, 0:09:57, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561480",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561618"
+        }
+    },
+    "models_modernbert": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 5,
+                "multi": 5
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 164,
+        "time_spent": "0:01:29, 0:01:27, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export",
+                    "trace": "(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm",
+                    "trace": "(line 401)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head",
+                    "trace": "(line 423)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification",
+                    "trace": "(line 469)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification",
+                    "trace": "(line 446)  AssertionError: Tensor-likes are not close!"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_export",
+                    "trace": "(line 675)  AssertionError: Lists differ: ['mechanic', 'lawyer', 'teacher', 'waiter', 'doctor'] != ['lawyer', 'mechanic', 'teacher', 'doctor', 'waiter']"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_masked_lm",
+                    "trace": "(line 401)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_no_head",
+                    "trace": "(line 423)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_sequence_classification",
+                    "trace": "(line 469)  AssertionError: Tensor-likes are not close!"
+                },
+                {
+                    "line": "tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelIntegrationTest::test_inference_token_classification",
+                    "trace": "(line 446)  AssertionError: Tensor-likes are not close!"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561668",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526561515"
+        }
+    },
+    "models_qwen2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 438,
+        "time_spent": "0:02:17, 0:02:18, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
+                    "trace": "(line 1642)  torch._dynamo.exc.TorchRuntimeError: Dynamo failed to run FX node with fake tensors: call_method index_copy_(*(FakeTensor(..., size=(1, 2, 26, 64), dtype=torch.bfloat16), 2, FakeTensor(..., device='cuda:0', size=(1,), dtype=torch.int64), FakeTensor(..., device='cuda:0', size=(1, 2, 1, 64), dtype=torch.bfloat16,"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562376",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562270"
+        }
+    },
+    "models_qwen2_5_omni": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 5
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 277,
+        "time_spent": "0:03:01, 0:03:21, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism",
+                    "trace": "(line 675)  AssertionError: Items in the second set but not the first:"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\"sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.\"] != [\"sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.\"]"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_multiturn",
+                    "trace": "(line 849)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 1 has a total capacity of 22.18 GiB of which 6.50 MiB is free. Process 51940 has 22.17 GiB memory in use. Of the allocated memory 21.74 GiB is allocated by PyTorch, and 27.83 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"
+                },
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_w_audio",
+                    "trace": "(line 1000)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 1 has a total capacity of 22.18 GiB of which 8.50 MiB is free. Process 51940 has 22.17 GiB memory in use. Of the allocated memory 21.75 GiB is allocated by PyTorch, and 17.78 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\"sys[96 chars]ant\\nsystem\\nYou are a helpful assistant.\\nuse[129 chars]er.\"] != [\"sys[96 chars]ant\\nThe sound is glass shattering, and the do[198 chars]er.\"]"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562375",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562289"
+        }
+    },
+    "models_qwen2_5_vl": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 311,
+        "time_spent": "0:03:25, 0:03:29, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
+                    "trace": "(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
+                    "trace": "(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562382",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562290"
+        }
+    },
+    "models_smolvlm": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 499,
+        "time_spent": "0:01:55, 0:01:47, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/smolvlm/test_modeling_smolvlm.py::SmolVLMForConditionalGenerationModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562675",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562798"
+        }
+    },
+    "models_t5": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 3
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 592,
+        "time_spent": "0:03:34, 0:03:41, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
+                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
+                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563047",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526562939"
+        }
+    },
+    "models_vit": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 217,
+        "time_spent": "7.34, 0:01:09, ",
+        "failures": {},
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563537",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563397"
+        }
+    },
+    "models_wav2vec2": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 4,
+                "multi": 4
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 672,
+        "time_spent": "0:04:46, 0:04:23, ",
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool",
+                    "trace": "(line 675)  AssertionError: Traceback (most recent call last):"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool",
+                    "trace": "(line 675)  AssertionError: Traceback (most recent call last):"
+                },
+                {
+                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool",
+                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563711",
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563582"
+        }
+    },
+    "models_whisper": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 8,
+                "multi": 11
+            },
+            "TensorFlow": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Flax": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Tokenizers": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Pipelines": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Trainer": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "ONNX": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Auto": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Quantization": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            },
+            "Unclassified": {
+                "unclassified": 0,
+                "single": 0,
+                "multi": 0
+            }
+        },
+        "success": 1010,
+        "time_spent": "0:12:29, 0:14:19, ",
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!'] != [\" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!']"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[422 chars]to a fisher shows in lip-nitsky attack that cu[7903 chars]le!\"] != [\" Fo[422 chars]to a Fisher shows in lip-nitsky attack that cu[7918 chars]le.\"]"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.\"] != [\" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.\"]"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_forced_decoder_ids",
+                    "trace": "(line 713)  requests.exceptions.ReadTimeout: (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 13cb0b08-c261-4ca3-a58f-91a2f3e327ed)')"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
+                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!'] != [\" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!']"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[422 chars]to a fisher shows in lip-nitsky attack that cu[7903 chars]le!\"] != [\" Fo[422 chars]to a Fisher shows in lip-nitsky attack that cu[7918 chars]le.\"]"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
+                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.\"] != [\" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.\"]"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_eager_padding_matches_padding_free_with_position_ids",
+                    "trace": "(line 4140)  KeyError: 'eager'"
+                },
+                {
+                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_multi_gpu_data_parallel_forward",
+                    "trace": "(line 1305)  AttributeError: 'DynamicCache' object has no attribute 'layers'"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563737",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/16460401119/job/46526563862"
+        }
+    }
+}