PaddleOCR paddleocr-vl-api容器报错：【RuntimeError: Exception from the 'vlm' worker: Connection error.】

🔎 Search before asking

[x] I have searched the PaddleOCR Docs and found no similar bug report.
[x] I have searched the PaddleOCR Issues and found no similar bug report.
[x] I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

一、镜像信息

aigc@aigc-SYS-4028GR-TR2-1-EC028:/raid/aigc/ocr/paddleocr_vl$ docker image ls | grep paddle ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl latest-offline 0843f08c7c70 29 hours ago 10.6GB ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-genai-vllm-server latest-offline 4de41c8b4b6f 7 days ago 14.7GB

二、部署 paddleocr-genai-vllm-server

cat /raid/aigc/ocr/paddleocr_vl/vllm_config.yaml

注：输出信息如下：
gpu-memory-utilization: 0.65
max-num-seqs: 128

docker run
-it
--rm
--gpus all
--network host
--name paddleocr-genai-vllm-server
-v /raid/aigc/ocr/paddleocr_vl/vllm_config.yaml:/home/paddleocr/pipeline_config.yaml
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-genai-vllm-server:latest-offline
paddleocr genai_server --model_name PaddleOCR-VL-0.9B --host 0.0.0.0 --port 8118 --backend vllm --backend_config /home/paddleocr/pipeline_config.yaml

三、部署 paddleocr-vl-api

cat PaddleOCR-VL.yaml

注：输出信息如下：

pipeline_name: PaddleOCR-VL

batch_size: 64

use_queues: True

use_doc_preprocessor: False
use_layout_detection: True
use_chart_recognition: False
format_block_content: False

SubModules:
  LayoutDetection:
	module_name: layout_detection
	model_name: PP-DocLayoutV2
	model_dir: null
	batch_size: 8
	threshold:
	  0: 0.5 # abstract
	  1: 0.5 # algorithm
	  2: 0.5 # aside_text
	  3: 0.5 # chart
	  4: 0.5 # content
	  5: 0.4 # formula
	  6: 0.4 # doc_title
	  7: 0.5 # figure_title
	  8: 0.5 # footer
	  9: 0.5 # footer
	  10: 0.5 # footnote
	  11: 0.5 # formula_number
	  12: 0.5 # header
	  13: 0.5 # header
	  14: 0.5 # image
	  15: 0.4 # formula
	  16: 0.5 # number
	  17: 0.4 # paragraph_title
	  18: 0.5 # reference
	  19: 0.5 # reference_content
	  20: 0.45 # seal
	  21: 0.5 # table
	  22: 0.4 # text
	  23: 0.4 # text
	  24: 0.5 # vision_footnote
	layout_nms: True
	layout_unclip_ratio: [1.0, 1.0]
	layout_merge_bboxes_mode:
	  0: "union" # abstract
	  1: "union" # algorithm
	  2: "union" # aside_text
	  3: "large" # chart
	  4: "union" # content
	  5: "large" # display_formula
	  6: "large" # doc_title
	  7: "union" # figure_title
	  8: "union" # footer
	  9: "union" # footer
	  10: "union" # footnote
	  11: "union" # formula_number
	  12: "union" # header
	  13: "union" # header
	  14: "union" # image
	  15: "large" # inline_formula
	  16: "union" # number
	  17: "large" # paragraph_title
	  18: "union" # reference
	  19: "union" # reference_content
	  20: "union" # seal
	  21: "union" # table
	  22: "union" # text
	  23: "union" # text
	  24: "union" # vision_footnote
  VLRecognition:
	module_name: vl_recognition
	model_name: PaddleOCR-VL-0.9B
	model_dir: null
	batch_size: 2048
	genai_config:
	  backend: vllm-server
	  server_url: http://10.0.12.252:8118/v1

SubPipelines:
  DocPreprocessor:
	pipeline_name: doc_preprocessor
	batch_size: 8
	use_doc_orientation_classify: True
	use_doc_unwarping: True
	SubModules:
	  DocOrientationClassify:
		module_name: doc_text_orientation
		model_name: PP-LCNet_x1_0_doc_ori
		model_dir: null
		batch_size: 8
	  DocUnwarping:
		module_name: image_unwarping
		model_name: UVDoc
		model_dir: null

cat compose.yaml

注：输出信息如下：
services:
  paddleocr-vl-api:
	image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl:latest-offline
	container_name: paddleocr-vl-api
	ports:
	  - 8080:8080
	volumes:
	  - /raid/aigc/ocr/paddleocr_vl/PaddleOCR-VL.yaml:/home/paddleocr/pipeline_config.yaml
	  - /raid/aigc/ocr/paddleocr_vl/vllm_config.yaml:/home/paddleocr/vllm_config.yaml
	  - /raid/aigc/ocr/img:/home/paddleocr/img
	deploy:
	  resources:
		reservations:
		  devices:
			- driver: nvidia
			  device_ids: ["0"]
			  capabilities: [gpu]
	restart: unless-stopped
	healthcheck:
	  test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]

docker compose up

注：输出信息如下：
[+] Running 1/1
 ✔ Container paddleocr-vl-api  Created                                                                                                                                                      0.0s
Attaching to paddleocr-vl-api
paddleocr-vl-api  | Creating model: ('PP-DocLayoutV2', None)
paddleocr-vl-api  | Model files already exist. Using cached files. To redownload, please delete the directory manually: `/home/paddleocr/.paddlex/official_models/PP-DocLayoutV2`.
paddleocr-vl-api  | /usr/local/lib/python3.10/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
paddleocr-vl-api  |   warnings.warn(warning_message)
paddleocr-vl-api  | Creating model: ('PaddleOCR-VL-0.9B', None)
paddleocr-vl-api  | INFO:     Started server process [1]
paddleocr-vl-api  | INFO:     Waiting for application startup.
paddleocr-vl-api  | INFO:     Application startup complete.
paddleocr-vl-api  | INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)


paddleocr-vl-api  | Unhandled exception
paddleocr-vl-api  | Traceback (most recent call last):
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, in __call__
paddleocr-vl-api  |     await self.app(scope, receive, _send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 63, in __call__
paddleocr-vl-api  |     await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
paddleocr-vl-api  |     raise exc
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
paddleocr-vl-api  |     await app(scope, receive, sender)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
paddleocr-vl-api  |     await self.app(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 716, in __call__
paddleocr-vl-api  |     await self.middleware_stack(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 736, in app
paddleocr-vl-api  |     await route.handle(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 290, in handle
paddleocr-vl-api  |     await self.app(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 125, in app
paddleocr-vl-api  |     await wrap_app_handling_exceptions(app, request)(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
paddleocr-vl-api  |     raise exc
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
paddleocr-vl-api  |     await app(scope, receive, sender)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 111, in app
paddleocr-vl-api  |     response = await f(request)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 391, in app
paddleocr-vl-api  |     raw_response = await run_endpoint_function(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 290, in run_endpoint_function
paddleocr-vl-api  |     return await dependant.call(**values)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_pipeline_apps/paddleocr_vl.py", line 54, in _infer
paddleocr-vl-api  |     result = await pipeline.infer(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 104, in infer
paddleocr-vl-api  |     return await self.call(_infer, *args, **kwargs)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 111, in call
paddleocr-vl-api  |     return await fut
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 126, in _worker
paddleocr-vl-api  |     result = func(*args, **kwargs)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 95, in _infer
paddleocr-vl-api  |     for item in it:
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/pipelines/_parallel.py", line 129, in predict
paddleocr-vl-api  |     yield from self._pipeline.predict(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/pipelines/paddleocr_vl/pipeline.py", line 673, in predict
paddleocr-vl-api  |     raise RuntimeError(
paddleocr-vl-api  | RuntimeError: Exception from the 'vlm' worker: Connection error.
paddleocr-vl-api  | INFO:     1.1.1.1:6004 - "POST /layout-parsing HTTP/1.1" 500 Internal Server Error
paddleocr-vl-api  | ERROR:    Exception in ASGI application
paddleocr-vl-api  | Traceback (most recent call last):
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
paddleocr-vl-api  |     result = await app(  # type: ignore[func-returns-value]
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
paddleocr-vl-api  |     return await self.app(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/applications.py", line 1134, in __call__
paddleocr-vl-api  |     await super().__call__(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/applications.py", line 113, in __call__
paddleocr-vl-api  |     await self.middleware_stack(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 186, in __call__
paddleocr-vl-api  |     raise exc
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, in __call__
paddleocr-vl-api  |     await self.app(scope, receive, _send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 63, in __call__
paddleocr-vl-api  |     await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
paddleocr-vl-api  |     raise exc
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
paddleocr-vl-api  |     await app(scope, receive, sender)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
paddleocr-vl-api  |     await self.app(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 716, in __call__
paddleocr-vl-api  |     await self.middleware_stack(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 736, in app
paddleocr-vl-api  |     await route.handle(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 290, in handle
paddleocr-vl-api  |     await self.app(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 125, in app
paddleocr-vl-api  |     await wrap_app_handling_exceptions(app, request)(scope, receive, send)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
paddleocr-vl-api  |     raise exc
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
paddleocr-vl-api  |     await app(scope, receive, sender)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 111, in app
paddleocr-vl-api  |     response = await f(request)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 391, in app
paddleocr-vl-api  |     raw_response = await run_endpoint_function(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 290, in run_endpoint_function
paddleocr-vl-api  |     return await dependant.call(**values)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_pipeline_apps/paddleocr_vl.py", line 54, in _infer
paddleocr-vl-api  |     result = await pipeline.infer(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 104, in infer
paddleocr-vl-api  |     return await self.call(_infer, *args, **kwargs)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 111, in call
paddleocr-vl-api  |     return await fut
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 126, in _worker
paddleocr-vl-api  |     result = func(*args, **kwargs)
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/serving/basic_serving/_app.py", line 95, in _infer
paddleocr-vl-api  |     for item in it:
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/pipelines/_parallel.py", line 129, in predict
paddleocr-vl-api  |     yield from self._pipeline.predict(
paddleocr-vl-api  |   File "/usr/local/lib/python3.10/site-packages/paddlex/inference/pipelines/paddleocr_vl/pipeline.py", line 673, in predict
paddleocr-vl-api  |     raise RuntimeError(
paddleocr-vl-api  | RuntimeError: Exception from the 'vlm' worker: Connection error.

附加信息：调用【POST /layout-parsing】接口，产生了上述报错信息。

Request body：
{
  "file": "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",
  "fileType": 1
}

附加说明：在paddleocr-vl-api容器中，执行下述命令（paddleocr doc_parser...）能够正常返回识别结果。（也就是说 paddleocr-genai-vllm-server 没问题，paddleocr-vl-api 有问题）

paddleocr@e9435bb1748e:~$ paddleocr doc_parser --input /home/paddleocr/img/ocr_small.png --vl_rec_backend vllm-server --vl_rec_server_url http://10.0.12.252:8118/v1

/usr/local/lib/python3.10/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
  warnings.warn(warning_message)
Creating model: ('PP-DocLayoutV2', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `/home/paddleocr/.paddlex/official_models/PP-DocLayoutV2`.
Creating model: ('PaddleOCR-VL-0.9B', None)
[2025/11/11 06:31:54] paddleocr INFO: Processed item 0 in 56448.272705078125 ms
{'res': {'input_path': '/home/paddleocr/img/ocr_small.png', 'page_index': None, 'model_settings': {'use_doc_preprocessor': False, 'use_layout_detection': True, 'use_chart_recognition': False, 'format_block_content': False}, 'layout_det_res': {'input_path': None, 'page_index': None, 'boxes': [{'cls_id': 17, 'label': 'paragraph_title', 'score': 0.9313395619392395, 'coordinate': [np.float32(6.630951), np.float32(8.1459465), np.float32(214.58302), np.float32(25.981472)]}]}, 'parsing_res_list': [{'block_label': 'paragraph_title', 'block_content': '你这个代码片段可以这样续写', 'block_bbox': [6, 8, 214, 25]}]}}

🏃‍♂️ Environment (运行环境)

OS Ubuntu-22.04.1 GPU NVIDIA GeForce RTX 2080 Ti Driver 580.105.08 CUDA 13.0

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

import os import base64 import requests import pathlib

API_URL = "http://10.0.12.252:8080/layout-parsing" image_path = "/raid/aigc/ocr/img/ocr_small.png" with open(image_path, "rb") as file: image_bytes = file.read() image_data = base64.b64encode(image_bytes).decode("ascii")

payload = { "file": image_data, # Base64编码的文件内容或者文件URL "fileType": 1, # 文件类型，1表示图像文件 } response = requests.post(API_URL, json=payload) assert response.status_code == 200

Nov 11 '25 08:11 wssunjiale

我也遇到了同一个错误

Nov 11 '25 08:11 myholiday

docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl:latest-offline 你只需要更新一下最新镜像，然后rm一下你的docker-compose，再启动一下就行了

Nov 11 '25 08:11 myholiday

docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl:latest-offline 你只需要更新一下最新镜像，然后rm一下你的docker-compose，再启动一下就行了

但是我的镜像已经是最新的了

Nov 11 '25 08:11 wssunjiale

@wssunjiale 观察到您是手动启动了vllm-server容器，然后docker compose启动了paddleocr-vl-api容器，所以您在 compose.yaml 中需要加一个下面的选项，才能与容器外正常通信

network: host

Nov 12 '25 03:11 zhang-prog

@wssunjiale 观察到您是手动启动了vllm-server容器，然后docker compose启动了paddleocr-vl-api容器，所以您在 compose.yaml 中需要加一个下面的选项，才能与容器外正常通信
network: host

可是我在docker compose启动的paddleocr-vl-api容器中通过命令行是可以收到正确回复的呀？？？

Nov 13 '25 01:11 wssunjiale

好了吗？怎么解决的，我刚下的，也报这个错。头疼啊。

Nov 26 '25 08:11 jnn23

@wssunjiale 观察到您是手动启动了vllm-server容器，然后docker compose启动了paddleocr-vl-api容器，所以您在 compose.yaml 中需要加一个下面的选项，才能与容器外正常通信
network: host
可是我在docker compose启动的paddleocr-vl-api容器中通过命令行是可以收到正确回复的呀？？？

如果是手动进入paddleocr-vl-api容器，然后启动服务呢（而不是调用CLI）？

Nov 26 '25 09:11 Bobholamovic

@wssunjiale 观察到您是手动启动了vllm-server容器，然后docker compose启动了paddleocr-vl-api容器，所以您在 compose.yaml 中需要加一个下面的选项，才能与容器外正常通信
network: host
可是我在docker compose启动的paddleocr-vl-api容器中通过命令行是可以收到正确回复的呀？？？
如果是手动进入paddleocr-vl-api容器，然后启动服务呢（而不是调用CLI）？

在容器中执行【paddlex --serve --pipeline /home/paddleocr/pipeline_config_vllm.yaml --port 8081】，在外面调用，会报同样的错误

Dec 01 '25 06:12 wssunjiale

如果paddleocr doc_parser可以执行成功，paddlex --serve不行，说明配置文件/home/paddleocr/pipeline_config_vllm.yaml中的设置有问题。请在容器中查看/home/paddleocr/pipeline_config_vllm.yaml的server_url设置是否正确。

Dec 01 '25 07:12 Bobholamovic