Главная Обзор Помощь
Регистрация Вход
CRBC-MaaS-Platform-Project
/
LQDeployConfig
4
0
Ответвить 0
Файлы Задачи 0 Запросы на слияние 0 Вики
Ветка: master
Ветки Метки
LQDeployConfig
/
prod
/
models
/
minerU
/
tf_logs
/
minerU_transfer.logs

minerU_transfer.logs 22 KB
Постоянная ссылка История Исходник

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273 
  1. 

  2. ot@localhost minerU]# time docker exec -it mineru-api mineru -p /app/input -o /app/output --source modelscope
    3. 

  3. 2026-03-21 21:45:20.218 | INFO     | mineru.utils.engine_utils:get_vlm_engine:32 - Using vllm-engine as the inference engine for VLM.
    4. 

  4. Creating new Ultralytics Settings v0.0.6 file ✅ 
    5. 

  5. View Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'
    6. 

  6. Update Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.
    7. 

  7. Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/MinerU2.5-2509-1.2B
    8. 

  8. 2026-03-21 21:45:27,522 - modelscope - INFO - Got 14 files, start to download ...
    9. 

  9. Downloading [configuration.json]: 100%|████████████████████████████████████████████████████████████████████████████████████| 55.0/55.0 [00:00<00:00, 80.6B/s]Downloading [generation_config.json]: 100%|███████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 392B/s]Downloading [chat_template.json]: 100%|█████████████████████████████████████████████████████████████████████████████████| 1.03k/1.03k [00:00<00:00, 1.48kB/s]Downloading [added_tokens.json]: 100%|██████████████████████████████████████████████████████████████████████████████████████| 800/800 [00:00<00:00, 1.12kB/s]Downloading [config.json]: 100%|████████████████████████████████████████████████████████████████████████████████████████| 1.17k/1.17k [00:00<00:00, 1.68kB/s]Downloading [preprocessor_config.json]: 100%|█████████████████████████████████████████████████████████████████████████████████| 346/346 [00:00<00:00, 477B/s]Downloading [tokenizer_config.json]: 100%|██████████████████████████████████████████████████████████████████████████████| 8.87k/8.87k [00:00<00:00, 15.4kB/s]Downloading [video_preprocessor_config.json]: 100%|███████████████████████████████████████████████████████████████████████████| 346/346 [00:00<00:00, 585B/s]Downloading [README.md]: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 17.0k/17.0k [00:00<00:00, 27.5kB/s]Downloading [special_tokens_map.json]: 100%|████████████████████████████████████████████████████████████████████████████| 4.59k/4.59k [00:00<00:00, 6.66kB/s]Downloading [merges.txt]: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 1.59M/1.59M [00:01<00:00, 1.18MB/s]Downloading [vocab.json]: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 2.65M/2.65M [00:01<00:00, 2.39MB/s]Downloading [tokenizer.json]: 100%|█████████████████████████████████████████████████████████████████████████████████████| 6.71M/6.71M [00:01<00:00, 4.12MB/s]Downloading [model.safetensors]: 100%|██████████████████████████████████████████████████████████████████████████████████| 2.15G/2.15G [04:48<00:00, 8.00MB/s]Processing 14 items: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 14.0/14.0 [04:49<00:00, 20.6s/it]2026-03-21 21:50:16,530 - modelscope - INFO - Download model 'OpenDataLab/MinerU2.5-2509-1.2B' successfully.             | 1.00M/1.59M [00:01<00:00, 773kB/s]2026-03-21 21:50:16,532 - modelscope - INFO - Creating symbolic link [/root/.cache/modelscope/models/OpenDataLab/MinerU2.5-2509-1.2B].
    10. 

  10. 2026-03-21 21:50:16.536 | INFO     | mineru.backend.vlm.utils:enable_custom_logits_processors:55 - compute_capability: 9.0 >= 8.0 and vllm version: 0.10.1.1 >= 0.10.1, enable custom_logits_processors                                                                              | 3.00M/2.15G [00:01<17:34, 2.19MB/s]/usr/local/lib/python3.12/dist-packages/transformers/utils/hub.py:111: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.0%|█████████████████████████████████████████████████████████████████████████████████▉| 2.15G/2.15G [04:48<00:00, 7.92MB/s]  warnings.warn(
    11. 

  11. INFO 03-21 21:50:18 [__init__.py:241] Automatically detected platform cuda.
    12. 

  12. INFO 03-21 21:50:20 [utils.py:326] non-default args: {'model': '/root/.cache/modelscope/models/OpenDataLab/MinerU2___5-2509-1___2B', 'gpu_memory_utilization': 0.5, 'disable_log_stats': True, 'logits_processors': [<class 'mineru_vl_utils.logits_processor.vllm_v1_no_repeat_ngram.VllmV1NoRepeatNGramLogitsProcessor'>]}
    13. 

  13. INFO 03-21 21:50:27 [__init__.py:711] Resolved architecture: Qwen2VLForConditionalGeneration
    14. 

  14. INFO 03-21 21:50:27 [__init__.py:1750] Using max model len 16384
    15. 

  15. INFO 03-21 21:50:28 [scheduler.py:222] Chunked prefill is enabled with max_num_batched_tokens=16384.
    16. 

  16. WARNING 03-21 21:50:30 [__init__.py:2921] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing for more information. Reasons: CUDA is initialized
    17. 

  17. /usr/local/lib/python3.12/dist-packages/transformers/utils/hub.py:111: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
    18. 

  18.   warnings.warn(
    19. 

  19. INFO 03-21 21:50:34 [__init__.py:241] Automatically detected platform cuda.
    20. 

  20. (EngineCore_0 pid=339) INFO 03-21 21:50:35 [core.py:636] Waiting for init message from front-end.
    21. 

  21. (EngineCore_0 pid=339) INFO 03-21 21:50:35 [core.py:74] Initializing a V1 LLM engine (v0.10.1.1) with config: model='/root/.cache/modelscope/models/OpenDataLab/MinerU2___5-2509-1___2B', speculative_config=None, tokenizer='/root/.cache/modelscope/models/OpenDataLab/MinerU2___5-2509-1___2B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=16384, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=/root/.cache/modelscope/models/OpenDataLab/MinerU2___5-2509-1___2B, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":3,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":[],"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output","vllm.mamba_mixer2"],"use_inductor":true,"compile_sizes":[],"inductor_compile_config":{"enable_auto_functionalized_v2":false},"inductor_passes":{},"cudagraph_mode":1,"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph_capture_sizes":[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"pass_config":{},"max_capture_size":512,"local_cache_dir":null}
    22. 

  22. (EngineCore_0 pid=339) INFO 03-21 21:50:38 [parallel_state.py:1134] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0
    23. 

  23. (EngineCore_0 pid=339) INFO 03-21 21:50:39 [topk_topp_sampler.py:50] Using FlashInfer for top-p & top-k sampling.
    24. 

  24. (EngineCore_0 pid=339) INFO 03-21 21:50:41 [gpu_model_runner.py:1953] Starting to load model /root/.cache/modelscope/models/OpenDataLab/MinerU2___5-2509-1___2B...
    25. 

  25. (EngineCore_0 pid=339) INFO 03-21 21:50:41 [gpu_model_runner.py:1985] Loading model from scratch...
    26. 

  26. (EngineCore_0 pid=339) WARNING 03-21 21:50:41 [cuda.py:211] Current `vllm-flash-attn` has a bug inside vision module, so we use xformers backend instead. You can run `pip install flash-attn` to use flash-attention backend.
    27. 

  27. (EngineCore_0 pid=339) INFO 03-21 21:50:41 [cuda.py:328] Using Flash Attention backend on V1 engine.
    28. 

  28. Loading safetensors checkpoint shards:   0% Completed | 0/1 [00:00<?, ?it/s]
    29. 

  29. Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  1.20it/s]
    30. 

  30. Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  1.20it/s]
    31. 

  31. (EngineCore_0 pid=339) 
    32. 

  32. (EngineCore_0 pid=339) INFO 03-21 21:50:42 [default_loader.py:262] Loading weights took 1.00 seconds
    33. 

  33. (EngineCore_0 pid=339) INFO 03-21 21:50:43 [gpu_model_runner.py:2007] Model loading took 2.1647 GiB and 1.222923 seconds
    34. 

  34. (EngineCore_0 pid=339) INFO 03-21 21:50:43 [gpu_model_runner.py:2591] Encoder cache will be initialized with a budget of 16384 tokens, and profiled with 1 video items of the maximum feature size.
    35. 

  35. (EngineCore_0 pid=339) INFO 03-21 21:50:51 [backends.py:548] Using cache directory: /root/.cache/vllm/torch_compile_cache/b19ac70222/rank_0_0/backbone for vLLM's torch.compile
    36. 

  36. (EngineCore_0 pid=339) INFO 03-21 21:50:51 [backends.py:559] Dynamo bytecode transform time: 3.05 s
    37. 

  37. (EngineCore_0 pid=339) INFO 03-21 21:50:55 [backends.py:194] Cache the graph for dynamic shape for later use
    38. 

  38. (EngineCore_0 pid=339) INFO 03-21 21:51:09 [backends.py:215] Compiling a graph for dynamic shape takes 17.27 s
    39. 

  39. (EngineCore_0 pid=339) INFO 03-21 21:51:12 [monitor.py:34] torch.compile takes 20.33 s in total
    40. 

  40. (EngineCore_0 pid=339) /usr/local/lib/python3.12/dist-packages/torch/utils/cpp_extension.py:2356: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. 
    41. 

  41. (EngineCore_0 pid=339) If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'].
    42. 

  42. (EngineCore_0 pid=339)   warnings.warn(
    43. 

  43. (EngineCore_0 pid=339) INFO 03-21 21:51:58 [gpu_worker.py:276] Available KV cache memory: 65.01 GiB
    44. 

  44. (EngineCore_0 pid=339) INFO 03-21 21:51:58 [kv_cache_utils.py:849] GPU KV cache size: 5,680,496 tokens
    45. 

  45. (EngineCore_0 pid=339) INFO 03-21 21:51:58 [kv_cache_utils.py:853] Maximum concurrency for 16,384 tokens per request: 346.71x
    46. 

  46. Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|███████████████████████████████████████████████████████████████| 67/67 [00:02<00:00, 26.44it/s](EngineCore_0 pid=339) INFO 03-21 21:52:01 [gpu_model_runner.py:2708] Graph capturing finished in 3 secs, took 0.54 GiB
    47. 

  47. (EngineCore_0 pid=339) INFO 03-21 21:52:01 [core.py:214] init engine (profile, create kv cache, warmup model) took 78.24 seconds
    48. 

  48. INFO 03-21 21:52:03 [llm.py:298] Supported_tasks: ['generate']
    49. 

  49. 2026-03-21 21:52:03.271 | INFO     | mineru.backend.vlm.vlm_analyze:get_model:218 - get vllm-engine predictor cost: 396.87s
    50. 

  50. 2026-03-21 21:52:05.200 | INFO     | mineru.backend.hybrid.hybrid_analyze:get_batch_ratio:365 - hybrid batch ratio (auto, vram=140GB): 16
    51. 

  51. Adding requests: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:02<00:00, 13.47it/s]Processed prompts: 100%|███████████████████████████████████████████| 33/33 [00:05<00:00,  6.43it/s, est. speed input: 8959.59 toks/s, output: 1036.93 toks/s]Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/PDF-Extract-Kit-1.0
    52. 

  52. 2026-03-21 21:52:15,635 - modelscope - INFO - Got 1 files, start to download ...
    53. 

  53. Downloading [models/OCR/paddleocr_torch/ch_PP-OCRv5_det_infer.pth]: 100%|███████████████████████████████████████████████| 13.8M/13.8M [00:02<00:00, 6.13MB/s]Processing 1 items: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 1.00/1.00 [00:02<00:00, 2.38s/it]2026-03-21 21:52:18,012 - modelscope - INFO - Download model 'OpenDataLab/PDF-Extract-Kit-1.0' successfully.
    54. 

  54. 2026-03-21 21:52:18,012 - modelscope - INFO - Creating symbolic link [/root/.cache/modelscope/models/OpenDataLab/PDF-Extract-Kit-1.0].
    55. 

  55. Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/PDF-Extract-Kit-1.0
    56. 

  56. 2026-03-21 21:52:19,398 - modelscope - INFO - Got 1 files, start to download ...
    57. 

  57. Downloading [models/OCR/paddleocr_torch/ch_PP-OCRv4_rec_server_doc_infer.pth]: 100%|████████████████████████████████████| 96.5M/96.5M [00:11<00:00, 9.05MB/s]Processing 1 items: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 1.00/1.00 [00:11<00:00, 11.2s/it]2026-03-21 21:52:30,592 - modelscope - INFO - Download model 'OpenDataLab/PDF-Extract-Kit-1.0' successfully.
    58. 

  58. 2026-03-21 21:52:30,592 - modelscope - INFO - Target directory already exists, skipping creation.
    59. 

  59. Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/PDF-Extract-Kit-1.0
    60. 

  60. 2026-03-21 21:52:33,100 - modelscope - INFO - Got 1 files, start to download ...
    61. 

  61. Downloading [models/MFD/YOLO/yolo_v8_ft.pt]: 100%|████████████████████████████████████████████████████████████████████████| 334M/334M [00:23<00:00, 14.6MB/s]Processing 1 items: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 1.00/1.00 [00:24<00:00, 24.0s/it]2026-03-21 21:52:57,104 - modelscope - INFO - Download model 'OpenDataLab/PDF-Extract-Kit-1.0' successfully.
    62. 

  62. 2026-03-21 21:52:57,104 - modelscope - INFO - Target directory already exists, skipping creation.
    63. 

  63. Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/PDF-Extract-Kit-1.0
    64. 

  64. 2026-03-21 21:52:58,540 - modelscope - INFO - Got 7 files, start to download ...
    65. 

  65. Downloading [models/MFR/unimernet_hf_small_2503/generation_config.json]: 100%|████████████████████████████████████████████████| 191/191 [00:00<00:00, 258B/s]Downloading [models/MFR/unimernet_hf_small_2503/tokenizer_config.json]: 100%|███████████████████████████████████████████| 4.42k/4.42k [00:00<00:00, 6.08kB/s]Downloading [models/MFR/unimernet_hf_small_2503/README.md]: 100%|███████████████████████████████████████████████████████| 1.62k/1.62k [00:00<00:00, 2.16kB/s]Downloading [models/MFR/unimernet_hf_small_2503/special_tokens_map.json]: 100%|███████████████████████████████████████████████| 552/552 [00:00<00:00, 704B/s]Downloading [models/MFR/unimernet_hf_small_2503/config.json]: 100%|█████████████████████████████████████████████████████| 4.97k/4.97k [00:00<00:00, 5.15kB/s]Downloading [models/MFR/unimernet_hf_small_2503/tokenizer.json]: 100%|██████████████████████████████████████████████████| 3.42M/3.42M [00:01<00:00, 2.93MB/s]Downloading [models/MFR/unimernet_hf_small_2503/model.safetensors]: 100%|█████████████████████████████████████████████████| 773M/773M [01:37<00:00, 8.27MB/s]Processing 7 items: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 7.00/7.00 [01:38<00:00, 14.0s/it]2026-03-21 21:54:36,550 - modelscope - INFO - Download model 'OpenDataLab/PDF-Extract-Kit-1.0' successfully.██████████████████| 552/552 [00:00<00:00, 705B/s]2026-03-21 21:54:36,550 - modelscope - INFO - Target directory already exists, skipping creation.████████████████████████▉| 772M/773M [01:37<00:00, 8.19MB/s]MFD Predict: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:02<00:00, 16.23it/s]MFR Predict: 0it [00:00, ?it/s]et_hf_small_2503/tokenizer.json]: 100%|██████████████████████████████████████████████████| 3.42M/3.42M [00:01<00:00, 3.69MB/s]OCR-det: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 24/24 [00:02<00:00,  8.01it/s]2026-03-21 21:54:45.411 | INFO     | mineru.cli.common:_process_output:168 - local output dir is /app/output/83《中华人民共和国突发事件应对法》（主席令第69号（2019修订））/hybrid_auto
    66. 

  66. Adding requests: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 58.62it/s]Processed prompts: 100%|██████████████████████████████████████████████| 4/4 [00:02<00:00,  1.42it/s, est. speed input: 1985.20 toks/s, output: 620.54 toks/s]Adding requests: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 76/76 [00:00<00:00, 222.47it/s]Processed prompts: 100%|███████████████████████████████████████████| 76/76 [00:01<00:00, 44.71it/s, est. speed input: 2799.87 toks/s, output: 1063.92 toks/s]2026-03-21 21:54:51.432 | INFO     | mineru.cli.common:_process_output:168 - local output dir is /app/output/33《铸钢砂》（YBT5150-93）/hybrid_auto
    67. 

  67. /usr/lib/python3.12/multiprocessing/resource_tracker.py:279: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
    68. 

  68.   warnings.warn('resource_tracker: There appear to be %d '
    69. 

  69. 

  70. real    9m42.249s
    71. 

  71. user    0m0.247s
    72. 

  72. sys     0m0.344s
    73. 

  73. [root@localhost minerU]# 
    74.