2026-01-14 12:17:33.994370703 [W:onnxruntime:Default, device_discovery.cc:164 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:89 ReadFileContents Failed to open file: “/sys/class/drm/card0/device/vendor”
INFO: Started server process [1]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
2026-01-14 12:22:06.082 | WARNING | mineru.utils.pdf_page_id:get_end_page_id:8 - end_page_id is out of range, use images length
Start MinerU FastAPI Service:
API documentation:
/usr/local/lib/python3.12/dist-packages/torchvision/io/image.py:14: UserWarning: Failed to load image Python extension: ‘Could not load this library: /usr/local/lib/python3.12/dist-packages/torchvision/image.so’If you don’t plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
2026-01-14 12:22:07.925 | INFO | mineru.backend.vlm.utils:enable_custom_logits_processors:46 - compute_capability: 12.1 >= 8.0 and vllm version: 0.12.0+35a9f223.nv25.12.post1 >= 0.10.1, enable custom_logits_processors
INFO 01-14 12:22:11 [model.py:637] Resolved architecture: Qwen2VLForConditionalGeneration
INFO 01-14 12:22:11 [model.py:1750] Using max model len 16384
INFO 01-14 12:22:11 [scheduler.py:228] Chunked prefill is enabled with max_num_batched_tokens=2048.
WARNING 01-14 12:22:12 [system_utils.py:136] We must use the spawn multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to ‘spawn’. See Troubleshooting - vLLM for more information. Reasons: CUDA is initialized
2026-01-14 12:22:12.387995123 [W:onnxruntime:Default, device_discovery.cc:164 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:89 ReadFileContents Failed to open file: “/sys/class/drm/card0/device/vendor”
/usr/local/lib/python3.12/dist-packages/torchvision/io/image.py:14: UserWarning: Failed to load image Python extension: ‘Could not load this library: /usr/local/lib/python3.12/dist-packages/torchvision/image.so’If you don’t plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
(EngineCore_DP0 pid=85) INFO 01-14 12:22:14 [core.py:93] Initializing a V1 LLM engine (v0.12.0+35a9f223.nv25.12.post1) with config: model=’/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B’, speculative_config=None, tokenizer=‘/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B’, skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, 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, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend=‘auto’, disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser=‘’, reasoning_parser_plugin=‘’, enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01), seed=0, served_model_name=/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={‘level’: None, ‘mode’: <CompilationMode.VLLM_COMPILE: 3>, ‘debug_dump_path’: None, ‘cache_dir’: ‘’, ‘compile_cache_save_format’: ‘binary’, ‘backend’: ‘inductor’, ‘custom_ops’: [‘none’], ‘splitting_ops’: [‘vllm::unified_attention’, ‘vllm::unified_attention_with_output’, ‘vllm::unified_mla_attention’, ‘vllm::unified_mla_attention_with_output’, ‘vllm::mamba_mixer2’, ‘vllm::mamba_mixer’, ‘vllm::short_conv’, ‘vllm::linear_attention’, ‘vllm::plamo2_mamba_mixer’, ‘vllm::gdn_attention_core’, ‘vllm::kda_attention’, ‘vllm::sparse_attn_indexer’], ‘compile_mm_encoder’: False, ‘compile_sizes’: , ‘inductor_compile_config’: {‘enable_auto_functionalized_v2’: False, ‘combo_kernels’: True, ‘benchmark_combo_kernel’: True}, ‘inductor_passes’: {}, ‘cudagraph_mode’: <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, ‘cudagraph_num_of_warmups’: 1, ‘cudagraph_capture_sizes’: [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256], ‘cudagraph_copy_inputs’: False, ‘cudagraph_specialize_lora’: True, ‘use_inductor_graph_partition’: False, ‘pass_config’: {‘fuse_norm_quant’: False, ‘fuse_act_quant’: False, ‘fuse_attn_quant’: False, ‘eliminate_noops’: True, ‘enable_sp’: False, ‘fuse_gemm_comms’: False, ‘fuse_allreduce_rms’: False}, ‘max_cudagraph_capture_size’: 256, ‘dynamic_shapes_config’: {‘type’: <DynamicShapesType.BACKED: ‘backed’>}, ‘local_cache_dir’: None}
(EngineCore_DP0 pid=85) INFO 01-14 12:22:15 [parallel_state.py:1200] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.18.0.2:55963 backend=nccl
(EngineCore_DP0 pid=85) INFO 01-14 12:22:15 [parallel_state.py:1408] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0
(EngineCore_DP0 pid=85) The image processor of type Qwen2VLImageProcessor is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with use_fast=False. Note that this behavior will be extended to all models in a future release.
(EngineCore_DP0 pid=85) INFO 01-14 12:22:17 [gpu_model_runner.py:3467] Starting to load model /root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B…
(EngineCore_DP0 pid=85) INFO 01-14 12:22:30 [cuda.py:411] Using FLASH_ATTN attention backend out of potential backends: [‘FLASH_ATTN’, ‘FLASHINFER’, ‘TRITON_ATTN’, ‘FLEX_ATTENTION’]
Loading safetensors checkpoint shards: 0% Completed | 0/1 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:14<00:00, 14.31s/it]
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:14<00:00, 14.31s/it]
(EngineCore_DP0 pid=85)
(EngineCore_DP0 pid=85) INFO 01-14 12:22:44 [default_loader.py:308] Loading weights took 14.37 seconds
(EngineCore_DP0 pid=85) INFO 01-14 12:22:45 [gpu_model_runner.py:3549] Model loading took 2.1647 GiB memory and 27.718669 seconds
(EngineCore_DP0 pid=85) INFO 01-14 12:22:45 [gpu_model_runner.py:4306] Encoder cache will be initialized with a budget of 14175 tokens, and profiled with 1 video items of the maximum feature size.
(EngineCore_DP0 pid=85) Process EngineCore_DP0:
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] EngineCore failed to start.
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] Traceback (most recent call last):
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 834, in run_engine_core
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 610, in init
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] super().init(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 109, in init
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] num_gpu_blocks, num_cpu_blocks, kv_cache_config = self._initialize_kv_caches(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 235, in _initialize_kv_caches
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/abstract.py”, line 126, in determine_available_memory
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return self.collective_rpc(“determine_available_memory”)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/uniproc_executor.py”, line 75, in collective_rpc
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] result = run_method(self.driver_worker, method, args, kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py”, line 479, in run_method
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return func(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py”, line 124, in decorate_context
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return func(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py”, line 324, in determine_available_memory
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] self.model_runner.profile_run()
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py”, line 4322, in profile_run
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] dummy_encoder_outputs = self.model.embed_multimodal(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 1449, in embed_multimodal
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] video_embeddings = self._process_video_input(video_input)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 1402, in _process_video_input
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] video_embeds = self.visual(pixel_values_videos, grid_thw=grid_thw)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 747, in forward
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] x = blk(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 494, in forward
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] x = x + self.attn(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 403, in forward
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] output = self.flash_attn_varlen_func(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/vllm/vllm_flash_attn/flash_attn_interface.py”, line 233, in flash_attn_varlen_func
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] out, softmax_lse = torch.ops._vllm_fa2_C.varlen_fwd(
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] File “/usr/local/lib/python3.12/dist-packages/torch/_ops.py”, line 1251, in call
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] return self._op(*args, **kwargs)
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) ERROR 01-14 12:22:47 [core.py:843] RuntimeError: This flash attention build does not support headdim not being a multiple of 32.
(EngineCore_DP0 pid=85) Traceback (most recent call last):
(EngineCore_DP0 pid=85) File “/usr/lib/python3.12/multiprocessing/process.py”, line 314, in _bootstrap
(EngineCore_DP0 pid=85) self.run()
(EngineCore_DP0 pid=85) File “/usr/lib/python3.12/multiprocessing/process.py”, line 108, in run
(EngineCore_DP0 pid=85) self._target(*self._args, **self._kwargs)
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 847, in run_engine_core
(EngineCore_DP0 pid=85) raise e
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 834, in run_engine_core
(EngineCore_DP0 pid=85) engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 610, in init
(EngineCore_DP0 pid=85) super().init(
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 109, in init
(EngineCore_DP0 pid=85) num_gpu_blocks, num_cpu_blocks, kv_cache_config = self._initialize_kv_caches(
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py”, line 235, in _initialize_kv_caches
(EngineCore_DP0 pid=85) available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/abstract.py”, line 126, in determine_available_memory
(EngineCore_DP0 pid=85) return self.collective_rpc(“determine_available_memory”)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/uniproc_executor.py”, line 75, in collective_rpc
(EngineCore_DP0 pid=85) result = run_method(self.driver_worker, method, args, kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/serial_utils.py”, line 479, in run_method
(EngineCore_DP0 pid=85) return func(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/utils/_contextlib.py”, line 124, in decorate_context
(EngineCore_DP0 pid=85) return func(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py”, line 324, in determine_available_memory
(EngineCore_DP0 pid=85) self.model_runner.profile_run()
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py”, line 4322, in profile_run
(EngineCore_DP0 pid=85) dummy_encoder_outputs = self.model.embed_multimodal(
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 1449, in embed_multimodal
(EngineCore_DP0 pid=85) video_embeddings = self._process_video_input(video_input)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 1402, in _process_video_input
(EngineCore_DP0 pid=85) video_embeds = self.visual(pixel_values_videos, grid_thw=grid_thw)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 747, in forward
(EngineCore_DP0 pid=85) x = blk(
(EngineCore_DP0 pid=85) ^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 494, in forward
(EngineCore_DP0 pid=85) x = x + self.attn(
(EngineCore_DP0 pid=85) ^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1783, in _wrapped_call_impl
(EngineCore_DP0 pid=85) return self._call_impl(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py”, line 1794, in _call_impl
(EngineCore_DP0 pid=85) return forward_call(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py”, line 403, in forward
(EngineCore_DP0 pid=85) output = self.flash_attn_varlen_func(
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/vllm/vllm_flash_attn/flash_attn_interface.py”, line 233, in flash_attn_varlen_func
(EngineCore_DP0 pid=85) out, softmax_lse = torch.ops._vllm_fa2_C.varlen_fwd(
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) File “/usr/local/lib/python3.12/dist-packages/torch/_ops.py”, line 1251, in call
(EngineCore_DP0 pid=85) return self._op(*args, **kwargs)
(EngineCore_DP0 pid=85) ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=85) RuntimeError: This flash attention build does not support headdim not being a multiple of 32.
[rank0]:[W114 12:22:47.338328313 ProcessGroupNCCL.cpp:1564] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see Distributed communication package - torch.distributed — PyTorch 2.9 documentation (function operator())
INFO: 192.168.3.56:61603 - “POST /file_parse HTTP/1.1” 500 Internal Server Error
2026-01-14 12:22:48.277 | ERROR | mineru.cli.fast_api:parse_pdf:332 - Engine core initialization failed. See root cause above. Failed core proc(s): {}
Traceback (most recent call last):
File “/usr/local/bin/mineru-api”, line 7, in
sys.exit(main())
│ │ └
│ └
└ <module ‘sys’ (built-in)>
File “/usr/local/lib/python3.12/dist-packages/click/core.py”, line 1485, in call
return self.main(*args, **kwargs)
│ │ │ └ {}
│ │ └ ()
│ └ <function Command.main at 0xe08df7fd74c0>
└
File “/usr/local/lib/python3.12/dist-packages/click/core.py”, line 1406, in main
rv = self.invoke(ctx)
│ │ └ <click.core.Context object at 0xe08d07db6ed0>
│ └ <function Command.invoke at 0xe08df7fd71a0>
└
File “/usr/local/lib/python3.12/dist-packages/click/core.py”, line 1269, in invoke
return ctx.invoke(self.callback, **ctx.params)
│ │ │ │ │ └ {‘host’: ‘0.0.0.0’, ‘port’: 8000, ‘reload’: False}
│ │ │ │ └ <click.core.Context object at 0xe08d07db6ed0>
│ │ │ └ <function main at 0xe08d076e31a0>
│ │ └
│ └ <function Context.invoke at 0xe08df7fd63e0>
└ <click.core.Context object at 0xe08d07db6ed0>
File “/usr/local/lib/python3.12/dist-packages/click/core.py”, line 824, in invoke
return callback(*args, **kwargs)
│ │ └ {‘host’: ‘0.0.0.0’, ‘port’: 8000, ‘reload’: False}
│ └ ()
└ <function main at 0xe08d076e31a0>
File “/usr/local/lib/python3.12/dist-packages/click/decorators.py”, line 34, in new_func
return f(get_current_context(), *args, **kwargs)
│ │ │ └ {‘host’: ‘0.0.0.0’, ‘port’: 8000, ‘reload’: False}
│ │ └ ()
│ └ <function get_current_context at 0xe08df7facae0>
└ <function main at 0xe08d076e3380>
File “/usr/local/lib/python3.12/dist-packages/mineru/cli/fast_api.py”, line 362, in main
uvicorn.run(
│ └ <function run at 0xe08df801a200>
└ <module ‘uvicorn’ from ‘/usr/local/lib/python3.12/dist-packages/uvicorn/init.py’>
File “/usr/local/lib/python3.12/dist-packages/uvicorn/main.py”, line 594, in run
server.run()
│ └ <function Server.run at 0xe08df7df9d00>
└ <uvicorn.server.Server object at 0xe08d076e9280>
File “/usr/local/lib/python3.12/dist-packages/uvicorn/server.py”, line 67, in run
return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory())
│ │ │ │ │ │ └ <function Config.get_loop_factory at 0xe08df8019ee0>
│ │ │ │ │ └ <uvicorn.config.Config object at 0xe08d1fa70ec0>
│ │ │ │ └ <uvicorn.server.Server object at 0xe08d076e9280>
│ │ │ └ None
│ │ └ <function Server.serve at 0xe08df7df9da0>
│ └ <uvicorn.server.Server object at 0xe08d076e9280>
└ <function run at 0xe08df8207380>
File “/usr/lib/python3.12/asyncio/runners.py”, line 194, in run
return runner.run(main)
│ │ └ <coroutine object Server.serve at 0xe08d077191c0>
│ └ <function Runner.run at 0xe08df822e660>
└ <asyncio.runners.Runner object at 0xe08d076e8f80>
File “/usr/lib/python3.12/asyncio/runners.py”, line 118, in run
return self._loop.run_until_complete(task)
│ │ │ └ <Task pending name=‘Task-1’ coro=<Server.serve() running at /usr/local/lib/python3.12/dist-packages/uvicorn/server.py:71> wai…
│ │ └ <cyfunction Loop.run_until_complete at 0xe08d078462c0>
│ └ <uvloop.Loop running=True closed=False debug=False>
└ <asyncio.runners.Runner object at 0xe08d076e8f80>
File “/usr/local/lib/python3.12/dist-packages/uvicorn/protocols/http/httptools_impl.py”, line 416, in run_asgi
result = await app( # type: ignore[func-returns-value]
└ <uvicorn.middleware.proxy_headers.ProxyHeadersMiddleware object at 0xe08d07747d40>
File “/usr/local/lib/python3.12/dist-packages/uvicorn/middleware/proxy_headers.py”, line 60, in call
return await self.app(scope, receive, send)
│ │ │ │ └ <bound method RequestResponseCycle.send of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074490…
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ └ <fastapi.applications.FastAPI object at 0xe08d077934d0>
└ <uvicorn.middleware.proxy_headers.ProxyHeadersMiddleware object at 0xe08d07747d40>
File “/usr/local/lib/python3.12/dist-packages/fastapi/applications.py”, line 1135, in call
await super().call(scope, receive, send)
│ │ └ <bound method RequestResponseCycle.send of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074490…
│ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
└ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
File “/usr/local/lib/python3.12/dist-packages/starlette/applications.py”, line 107, in call
await self.middleware_stack(scope, receive, send)
│ │ │ │ └ <bound method RequestResponseCycle.send of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074490…
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ └ <starlette.middleware.errors.ServerErrorMiddleware object at 0xe08d07426420>
└ <fastapi.applications.FastAPI object at 0xe08d077934d0>
File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py”, line 164, in call
await self.app(scope, receive, _send)
│ │ │ │ └ <function ServerErrorMiddleware.call.._send at 0xe08d07440d60>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ └ <starlette.middleware.gzip.GZipMiddleware object at 0xe08d07426450>
└ <starlette.middleware.errors.ServerErrorMiddleware object at 0xe08d07426420>
File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/gzip.py”, line 29, in call
await responder(scope, receive, send)
│ │ │ └ <function ServerErrorMiddleware.call.._send at 0xe08d07440d60>
│ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
└ <starlette.middleware.gzip.GZipResponder object at 0xe08d07426ff0>
File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/gzip.py”, line 130, in call
await super().call(scope, receive, send)
│ │ └ <function ServerErrorMiddleware.call.._send at 0xe08d07440d60>
│ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
└ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/gzip.py”, line 46, in call
await self.app(scope, receive, self.send_with_compression)
│ │ │ │ │ └ <function IdentityResponder.send_with_compression at 0xe08df6f2fe20>
│ │ │ │ └ <starlette.middleware.gzip.GZipResponder object at 0xe08d07426ff0>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ └ <starlette.middleware.exceptions.ExceptionMiddleware object at 0xe08df8cdc860>
└ <starlette.middleware.gzip.GZipResponder object at 0xe08d07426ff0>
File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/exceptions.py”, line 63, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
│ │ │ │ │ │ └ <bound method IdentityResponder.send_with_compression of <starlette.middleware.gzip.GZipResponder object at 0xe08d07426ff0>>
│ │ │ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ │ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ │ │ └ <starlette.requests.Request object at 0xe08d073b75f0>
│ │ └ <fastapi.middleware.asyncexitstack.AsyncExitStackMiddleware object at 0xe08d07391430>
│ └ <starlette.middleware.exceptions.ExceptionMiddleware object at 0xe08df8cdc860>
└ <function wrap_app_handling_exceptions at 0xe08df6e8e0c0>
File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app
await app(scope, receive, sender)
│ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
└ <fastapi.middleware.asyncexitstack.AsyncExitStackMiddleware object at 0xe08d07391430>
File “/usr/local/lib/python3.12/dist-packages/fastapi/middleware/asyncexitstack.py”, line 18, in call
await self.app(scope, receive, send)
│ │ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), ‘c…
│ └ <fastapi.routing.APIRouter object at 0xe08d076e8b90>
└ <fastapi.middleware.asyncexitstack.AsyncExitStackMiddleware object at 0xe08d07391430>
File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 716, in call
await self.middleware_stack(scope, receive, send)
│ │ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), ‘c…
│ └ <bound method Router.app of <fastapi.routing.APIRouter object at 0xe08d076e8b90>>
└ <fastapi.routing.APIRouter object at 0xe08d076e8b90>
File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 736, in app
await route.handle(scope, receive, send)
│ │ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), ‘c…
│ └ <function Route.handle at 0xe08df6e8f560>
└ APIRoute(path=’/file_parse’, name=‘parse_pdf’, methods=[‘POST’])
File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 290, in handle
await self.app(scope, receive, send)
│ │ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), ‘c…
│ └ <function request_response..app at 0xe08d076e2f20>
└ APIRoute(path=’/file_parse’, name=‘parse_pdf’, methods=[‘POST’])
File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 119, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
│ │ │ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07440ea0>
│ │ │ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ │ │ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
│ │ └ <starlette.requests.Request object at 0xe08d07426c30>
│ └ <function request_response..app..app at 0xe08d07440f40>
└ <function wrap_app_handling_exceptions at 0xe08df6e8e0c0>
File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app
await app(scope, receive, sender)
│ │ │ └ <function wrap_app_handling_exceptions..wrapped_app..sender at 0xe08d07441080>
│ │ └ <bound method RequestResponseCycle.receive of <uvicorn.protocols.http.httptools_impl.RequestResponseCycle object at 0xe08d074…
│ └ {‘type’: ‘http’, ‘asgi’: {‘version’: ‘3.0’, ‘spec_version’: ‘2.3’}, ‘http_version’: ‘1.1’, ‘server’: (‘172.18.0.2’, 8000), 'c…
└ <function request_response..app..app at 0xe08d07440f40>
File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 105, in app
response = await f(request)
│ └ <starlette.requests.Request object at 0xe08d07426c30>
└ <function get_request_handler..app at 0xe08d076e3100>
File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 426, in app
raw_response = await run_endpoint_function(
└ <function run_endpoint_function at 0xe08df6ea94e0>
File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 312, in run_endpoint_function
return await dependant.call(**values)
│ │ └ {‘files’: [UploadFile(filename=‘en规范.pdf’, size=763496, headers=Headers({‘content-disposition’: 'form-data; name=“files”; fil…
│ └ <function parse_pdf at 0xe08d076e2ca0>
└ Dependant(path_params=, query_params=, header_params=, cookie_params=, body_params=[ModelField(field_info=File(Pydant…
File “/usr/local/lib/python3.12/dist-packages/mineru/cli/fast_api.py”, line 215, in parse_pdf
await aio_do_parse(
└ <function aio_do_parse at 0xe08d076e2160>
File “/usr/local/lib/python3.12/dist-packages/mineru/cli/common.py”, line 532, in aio_do_parse
await _async_process_vlm(
└ <function _async_process_vlm at 0xe08d076e1da0>
File “/usr/local/lib/python3.12/dist-packages/mineru/cli/common.py”, line 253, in _async_process_vlm
middle_json, infer_result = await aio_vlm_doc_analyze(
└ <function aio_doc_analyze at 0xe08d076e1a80>
File “/usr/local/lib/python3.12/dist-packages/mineru/backend/vlm/vlm_analyze.py”, line 230, in aio_doc_analyze
predictor = ModelSingleton().get_model(backend, model_path, server_url, **kwargs)
│ │ │ │ └ {‘gpu_memory_utilization’: 0.4}
│ │ │ └ None
│ │ └ None
│ └ ‘vllm-async-engine’
└ <class ‘mineru.backend.vlm.vlm_analyze.ModelSingleton’>
File “/usr/local/lib/python3.12/dist-packages/mineru/backend/vlm/vlm_analyze.py”, line 125, in get_model
vllm_async_llm = AsyncLLM.from_engine_args(AsyncEngineArgs(**kwargs))
│ │ │ └ {‘gpu_memory_utilization’: 0.4, ‘model’: ‘/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B’, ‘logits_pr…
│ │ └ <class ‘vllm.engine.arg_utils.AsyncEngineArgs’>
│ └ <classmethod(<function AsyncLLM.from_engine_args at 0xe08cd2a85bc0>)>
└ <class ‘vllm.v1.engine.async_llm.AsyncLLM’>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py”, line 252, in from_engine_args
return cls(
└ <class ‘vllm.v1.engine.async_llm.AsyncLLM’>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py”, line 134, in init
self.engine_core = EngineCoreClient.make_async_mp_client(
│ │ └ <staticmethod(<function EngineCoreClient.make_async_mp_client at 0xe08cd2a3e480>)>
│ └ <class ‘vllm.v1.engine.core_client.EngineCoreClient’>
└ <vllm.v1.engine.async_llm.AsyncLLM object at 0xe08cc8f7b0b0>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py”, line 121, in make_async_mp_client
return AsyncMPClient(*client_args)
│ └ (VllmConfig(model_config=ModelConfig(model=’/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B’, runner=‘…
└ <class ‘vllm.v1.engine.core_client.AsyncMPClient’>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py”, line 810, in init
super().init(
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py”, line 471, in init
with launch_core_engines(vllm_config, executor_class, log_stats) as (
│ │ │ └ True
│ │ └ <class ‘vllm.v1.executor.uniproc_executor.UniProcExecutor’>
│ └ VllmConfig(model_config=ModelConfig(model=’/root/.cache/modelscope/hub/models/OpenDataLab/MinerU2___5-2509-1___2B’, runner='a…
└ <function launch_core_engines at 0xe08cd2a33ba0>
File “/usr/lib/python3.12/contextlib.py”, line 144, in exit
next(self.gen)
│ └ <generator object launch_core_engines at 0xe08c24a24230>
└ <contextlib._GeneratorContextManager object at 0xe08cc8db5b80>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/utils.py”, line 903, in launch_core_engines
wait_for_engine_startup(
└ <function wait_for_engine_startup at 0xe08cd2a33c40>
File “/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/utils.py”, line 960, in wait_for_engine_startup
raise RuntimeError(
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}