Replies: 1 comment 2 replies
-
|
Hi @GuanJD! I'm Dosu and I’m helping the MinerU team. 你的报错是因为 MinerU 默认选择了 vllm-async-engine 作为后端,但 vllm 只支持 CUDA GPU,不支持纯 CPU 环境,导致 device string 为空,出现 “Device string must not be empty” 的错误,并且会有 CUDA 相关的警告和报错(如 libcuda.so.1 找不到)参考。 解决方法如下:
最简 CPU-only 启动示例: export MINERU_DEVICE_MODE=cpu
export CUDA_VISIBLE_DEVICES=""
mineru-api --host 0.0.0.0 --port 8000 --backend pipeline如还有问题,可以补充你的 backend 配置和完整启动命令。 To reply, just mention @dosu. How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
报错信息如下:
Start MinerU FastAPI Service: http://0.0.0.0:8000
API documentation: http://0.0.0.0:8000/docs
INFO: Started server process [74553]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
2026-01-28 17:16:42.087 | WARNING | mineru.utils.pdf_page_id:get_end_page_id:8 - end_page_id is out of range, use images length
2026-01-28 17:16:43.019 | INFO | mineru.utils.engine_utils:get_vlm_engine:32 - Using vllm-async-engine as the inference engine for VLM.
INFO 01-28 17:16:45 [init.py:220] No platform detected, vLLM is running on UnspecifiedPlatform
WARNING 01-28 17:16:46 [_custom_ops.py:20] Failed to import from vllm._C with ImportError('libcuda.so.1: cannot open shared object file: No such file or directory')
2026-01-28 17:16:47.025 | INFO | mineru.backend.vlm.utils:enable_custom_logits_processors:26 - CUDA not available, disabling custom_logits_processors
2026-01-28 17:16:47.039 | ERROR | mineru.cli.fast_api:parse_pdf:332 - Device string must not be empty
Beta Was this translation helpful? Give feedback.
All reactions