Upload 2025-12-22/runs/25849-20423647274/ci_results_run_models_gpu/model_results.json with huggingface_hub

2025-12-22/runs/25849-20423647274/ci_results_run_models_gpu/model_results.json

@@ -0,0 +1,403 @@
+{
+    "models_llava": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 10,
+                "multi": 9
+            },
+            "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
+            }
+        },
+        "errors": 0,
+        "success": 356,
+        "skipped": 253,
+        "time_spent": [
+            296.86,
+            292.09
+        ],
+        "error": false,
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
+                    "trace": "(line 562)  AssertionError: Lists differ: [\"\\n\\nUSER: What's the difference of two imag[339 chars]ama'] != [\"\\n \\nUSER: What's the difference of two ima[362 chars]the']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_generation_no_images",
+                    "trace": "(line 693)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 32.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 10.69 MiB is free. Process 17245 has 22.29 GiB memory in use. Of the allocated memory 21.88 GiB is allocated by PyTorch, and 24.45 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/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral",
+                    "trace": "(line 543)  RuntimeError: Input type (torch.FloatTensor) and weight type (CPUBFloat16Type) should be the same or input should be a MKLDNN tensor and weight is a dense tensor"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral_4bit",
+                    "trace": "(line 693)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 40.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 28.69 MiB is free. Process 17245 has 22.27 GiB memory in use. Of the allocated memory 21.88 GiB is allocated by PyTorch, and 9.70 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/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral_batched",
+                    "trace": "(line 693)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 140.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 126.69 MiB is free. Process 17245 has 22.17 GiB memory in use. Of the allocated memory 21.74 GiB is allocated by PyTorch, and 51.91 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/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_batched",
+                    "trace": "(line 404)  AssertionError: Lists differ: ['USER: \\nWhat are the things I should be cautiou[269 chars] on'] != ['USER:  \\nWhat are the things I should be cautio[271 chars] on']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_batched_regression",
+                    "trace": "(line 507)  AssertionError: Lists differ: ['USER: \\nWhat are the things I should be cautiou[280 chars]ed.'] != ['USER:  \\nWhat are the things I should be cautio[283 chars]ed.']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_single",
+                    "trace": "(line 353)  AssertionError: 'USER: \\nWhat are the things I should be cautiou[748 chars]ies.' != 'USER:  \\nWhat are the things I should be cautio[749 chars]ies.'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_tokenizer_integration",
+                    "trace": "(line 579)  AssertionError: Lists differ: ['<|im_start|>', '▁system', '\\n', '▁Answer', '▁the', '▁ques[176 chars]'\\n'] != ['<|im_start|>', 'system', '\\n', 'Answer', '▁the', '▁questi[175 chars]'\\n']"
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
+                    "trace": "(line 562)  AssertionError: Lists differ: [\"\\n\\nUSER: What's the difference of two imag[339 chars]ama'] != [\"\\n \\nUSER: What's the difference of two ima[362 chars]the']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral",
+                    "trace": "(line 543)  RuntimeError: Input type (torch.FloatTensor) and weight type (CPUBFloat16Type) should be the same or input should be a MKLDNN tensor and weight is a dense tensor"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral_4bit",
+                    "trace": "(line 693)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 40.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 16.69 MiB is free. Process 22505 has 22.28 GiB memory in use. Of the allocated memory 21.77 GiB is allocated by PyTorch, and 4.77 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/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_pixtral_batched",
+                    "trace": "(line 693)  torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 40.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 34.69 MiB is free. Process 22505 has 22.26 GiB memory in use. Of the allocated memory 21.73 GiB is allocated by PyTorch, and 30.40 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/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_batched",
+                    "trace": "(line 404)  AssertionError: Lists differ: ['USER: \\nWhat are the things I should be cautiou[269 chars] on'] != ['USER:  \\nWhat are the things I should be cautio[271 chars] on']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_batched_regression",
+                    "trace": "(line 507)  AssertionError: Lists differ: ['USER: \\nWhat are the things I should be cautiou[280 chars]ed.'] != ['USER:  \\nWhat are the things I should be cautio[283 chars]ed.']"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_small_model_integration_test_llama_single",
+                    "trace": "(line 353)  AssertionError: 'USER: \\nWhat are the things I should be cautiou[748 chars]ies.' != 'USER:  \\nWhat are the things I should be cautio[749 chars]ies.'"
+                },
+                {
+                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_tokenizer_integration",
+                    "trace": "(line 579)  AssertionError: Lists differ: ['<|im_start|>', '▁system', '\\n', '▁Answer', '▁the', '▁ques[176 chars]'\\n'] != ['<|im_start|>', 'system', '\\n', 'Answer', '▁the', '▁questi[175 chars]'\\n']"
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144221",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144228"
+        },
+        "captured_info": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144221#step:16:1",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144228#step:16:1"
+        }
+    },
+    "models_llava_next": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 2,
+                "multi": 2
+            },
+            "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
+            }
+        },
+        "errors": 0,
+        "success": 359,
+        "skipped": 139,
+        "time_spent": [
+            461.77,
+            477.34
+        ],
+        "error": false,
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llava_next/test_modeling_llava_next.py::LlavaNextForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_next/test_modeling_llava_next.py::LlavaNextForConditionalGenerationIntegrationTest::test_small_model_integration_test_unk_token",
+                    "trace": "(line 424)  AssertionError: '[INS[24 chars]his  image? [/INST] The image appears to be a [185 chars]hart' != '[INS[24 chars]his   image? [/INST] The image appears to be a[186 chars]hart'"
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llava_next/test_modeling_llava_next.py::LlavaNextForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_next/test_modeling_llava_next.py::LlavaNextForConditionalGenerationIntegrationTest::test_small_model_integration_test_unk_token",
+                    "trace": "(line 424)  AssertionError: '[INS[24 chars]his  image? [/INST] The image appears to be a [185 chars]hart' != '[INS[24 chars]his   image? [/INST] The image appears to be a[186 chars]hart'"
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144225",
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144216"
+        },
+        "captured_info": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144225#step:16:1",
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144216#step:16:1"
+        }
+    },
+    "models_llava_next_video": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 3,
+                "multi": 3
+            },
+            "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
+            }
+        },
+        "errors": 0,
+        "success": 365,
+        "skipped": 107,
+        "time_spent": [
+            234.03,
+            226.99
+        ],
+        "error": false,
+        "failures": {
+            "single": [
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationIntegrationTest::test_small_model_integration_test",
+                    "trace": "(line 377)  AssertionError: 'USER[154 chars]hile wearing a pair of glasses that are too la[25 chars] are' != 'USER[154 chars]hile another child is attempting to read the s[45 chars]eems'"
+                },
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationIntegrationTest::test_small_model_integration_test_batch_matches_single",
+                    "trace": "(line 469)  AssertionError: 'USER: \\nWhy is this video funny? ASSISTA[254 chars]them' != \"USER: \\nWhy is this video funny? ASSISTA[231 chars]eyes\""
+                }
+            ],
+            "multi": [
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationIntegrationTest::test_small_model_integration_test",
+                    "trace": "(line 377)  AssertionError: 'USER[154 chars]hile wearing a pair of glasses that are too la[25 chars] are' != 'USER[154 chars]hile another child is attempting to read the s[45 chars]eems'"
+                },
+                {
+                    "line": "tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationIntegrationTest::test_small_model_integration_test_batch_matches_single",
+                    "trace": "(line 469)  AssertionError: 'USER: \\nWhy is this video funny? ASSISTA[254 chars]them' != \"USER: \\nWhy is this video funny? ASSISTA[231 chars]eyes\""
+                }
+            ]
+        },
+        "job_link": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144232",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144213"
+        },
+        "captured_info": {
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144232#step:16:1",
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144213#step:16:1"
+        }
+    },
+    "models_llava_onevision": {
+        "failed": {
+            "PyTorch": {
+                "unclassified": 0,
+                "single": 1,
+                "multi": 1
+            },
+            "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": 2,
+                "multi": 2
+            }
+        },
+        "errors": 0,
+        "success": 411,
+        "skipped": 115,
+        "time_spent": [
+            179.8,
+            179.54
+        ],
+        "error": false,
+        "failures": {
+            "multi": [
+                {
+                    "line": "tests/models/llava_onevision/test_modeling_llava_onevision.py::LlavaOnevisionForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_onevision/test_processing_llava_onevision.py::LlavaOnevisionProcessorTest::test_apply_chat_template_video_0",
+                    "trace": "(line 707)  TypeError: Incorrect format used for video. Should be an url linking to an video or a local path."
+                },
+                {
+                    "line": "tests/models/llava_onevision/test_processing_llava_onevision.py::LlavaOnevisionProcessorTest::test_apply_chat_template_video_1",
+                    "trace": "(line 707)  TypeError: Incorrect format used for video. Should be an url linking to an video or a local path."
+                }
+            ],
+            "single": [
+                {
+                    "line": "tests/models/llava_onevision/test_modeling_llava_onevision.py::LlavaOnevisionForConditionalGenerationModelTest::test_all_tensors_are_parameter_or_buffer",
+                    "trace": "(line 2542)  RuntimeError: Expected all tensors to be on the same device, but got index is on cuda:0, different from other tensors on cpu (when checking argument in method wrapper_CUDA__index_select)"
+                },
+                {
+                    "line": "tests/models/llava_onevision/test_processing_llava_onevision.py::LlavaOnevisionProcessorTest::test_apply_chat_template_video_0",
+                    "trace": "(line 707)  TypeError: Incorrect format used for video. Should be an url linking to an video or a local path."
+                },
+                {
+                    "line": "tests/models/llava_onevision/test_processing_llava_onevision.py::LlavaOnevisionProcessorTest::test_apply_chat_template_video_1",
+                    "trace": "(line 707)  TypeError: Incorrect format used for video. Should be an url linking to an video or a local path."
+                }
+            ]
+        },
+        "job_link": {
+            "multi": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144255",
+            "single": "https://github.com/huggingface/transformers/actions/runs/20423647274/job/58680144234"
+        },
+        "captured_info": {}
+    }
+}