ot@localhost minerU]# time docker exec -it mineru-api mineru -p /app/input -o /app/output --source modelscope 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. Creating new Ultralytics Settings v0.0.6 file ✅ View Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json' 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. Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/models/OpenDataLab/MinerU2.5-2509-1.2B 2026-03-21 21:45:27,522 - modelscope - INFO - Got 14 files, start to download ... 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]. 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( INFO 03-21 21:50:18 [__init__.py:241] Automatically detected platform cuda. 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': []} INFO 03-21 21:50:27 [__init__.py:711] Resolved architecture: Qwen2VLForConditionalGeneration INFO 03-21 21:50:27 [__init__.py:1750] Using max model len 16384 INFO 03-21 21:50:28 [scheduler.py:222] Chunked prefill is enabled with max_num_batched_tokens=16384. 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 /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. warnings.warn( INFO 03-21 21:50:34 [__init__.py:241] Automatically detected platform cuda. (EngineCore_0 pid=339) INFO 03-21 21:50:35 [core.py:636] Waiting for init message from front-end. (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} (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 (EngineCore_0 pid=339) INFO 03-21 21:50:39 [topk_topp_sampler.py:50] Using FlashInfer for top-p & top-k sampling. (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... (EngineCore_0 pid=339) INFO 03-21 21:50:41 [gpu_model_runner.py:1985] Loading model from scratch... (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. (EngineCore_0 pid=339) INFO 03-21 21:50:41 [cuda.py:328] Using Flash Attention backend on V1 engine. Loading safetensors checkpoint shards: 0% Completed | 0/1 [00:00