Mirrors/dots.ocr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
46 Commits 1 Branch 0 Tags
b29ef43aeb0fd5b7ad8350eab63ab3bf65248489
Commit Graph

46 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
gnothi b29ef43aeb Update vllm version for Colab notebook 
new version if vllm (0.10.1) break hosting on Colab.

```error_log
(EngineCore_0 pid=4952)   File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/qwen2_vl.py", line 769, in get_image_processor
(EngineCore_0 pid=4952)     return self.get_hf_processor(**kwargs).image_processor
(EngineCore_0 pid=4952)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=4952)   File "/content/dots.ocr/weights/DotsOCR/modeling_dots_ocr_vllm.py", line 113, in get_hf_processor
(EngineCore_0 pid=4952)     self.get_tokenizer().image_token = "<|imgpad|>" # Ensure image token is set
(EngineCore_0 pid=4952)     ^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=4952) RecursionError: maximum recursion depth exceeded
[rank0]:[W820 01:47:10.202570866 ProcessGroupNCCL.cpp:1479] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
(APIServer pid=4825) Traceback (most recent call last):
(APIServer pid=4825)   File "/usr/local/bin/vllm", line 9, in <module>
(APIServer pid=4825)     sys.exit(main())
(APIServer pid=4825)              ^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/main.py", line 54, in main
(APIServer pid=4825)     args.dispatch_function(args)
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/serve.py", line 50, in cmd
(APIServer pid=4825)     uvloop.run(run_server(args))
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 109, in run
(APIServer pid=4825)     return __asyncio.run(
(APIServer pid=4825)            ^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run
(APIServer pid=4825)     return runner.run(main)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
(APIServer pid=4825)     return self._loop.run_until_complete(task)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 61, in wrapper
(APIServer pid=4825)     return await main
(APIServer pid=4825)            ^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1850, in run_server
(APIServer pid=4825)     await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1870, in run_server_worker
(APIServer pid=4825)     async with build_async_engine_client(
(APIServer pid=4825)                ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=4825)     return await anext(self.gen)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 178, in build_async_engine_client
(APIServer pid=4825)     async with build_async_engine_client_from_engine_args(
(APIServer pid=4825)                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=4825)     return await anext(self.gen)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 220, in build_async_engine_client_from_engine_args
(APIServer pid=4825)     async_llm = AsyncLLM.from_vllm_config(
(APIServer pid=4825)                 ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/utils/__init__.py", line 1557, in inner
(APIServer pid=4825)     return fn(*args, **kwargs)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 174, in from_vllm_config
(APIServer pid=4825)     return cls(
(APIServer pid=4825)            ^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 120, in __init__
(APIServer pid=4825)     self.engine_core = EngineCoreClient.make_async_mp_client(
(APIServer pid=4825)                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 102, in make_async_mp_client
(APIServer pid=4825)     return AsyncMPClient(*client_args)
(APIServer pid=4825)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 767, in __init__
(APIServer pid=4825)     super().__init__(
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 446, in __init__
(APIServer pid=4825)     with launch_core_engines(vllm_config, executor_class,
(APIServer pid=4825)          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=4825)   File "/usr/lib/python3.12/contextlib.py", line 144, in __exit__
(APIServer pid=4825)     next(self.gen)
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/utils.py", line 706, in launch_core_engines
(APIServer pid=4825)     wait_for_engine_startup(
(APIServer pid=4825)   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/utils.py", line 759, in wait_for_engine_startup
(APIServer pid=4825)     raise RuntimeError("Engine core initialization failed. "
(APIServer pid=4825) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}```
 2025-08-20 11:42:59 +09:00
zhangwei13 23a48b5ab1 fix wechat & add X 2025-08-18 12:13:01 +08:00
Qing Yan 2a5977c597 Merge pull request #93 from gc-fu/patch-1 
Fix not used arguments in demo_vllm.py
 2025-08-13 16:51:51 +08:00
Guancheng Fu ffd5e81103 Update demo_vllm.py 2025-08-13 15:52:01 +08:00
zhangwei13 4a37ed0eab Merge branch 'master' of github.com:rednote-hilab/dots.ocr 2025-08-12 16:07:36 +08:00
zhangwei13 377764d029 update license 2025-08-12 16:07:22 +08:00
Qing Yan 092460a8a2 Merge pull request #62 from louisoutin/master 
Add Google Colab (free) notebook demo
 2025-08-12 10:00:56 +08:00
zhangwei13 8871d29d8b update agreement 2025-08-11 10:30:23 +08:00
zhangwei13 6a854390b4 add fitz_preprocess as default preprocess for image parser to align with demo 2025-08-11 09:44:05 +08:00
zhangwei13 af3a52fa32 add fitz_preprocess as default preprocess for image parser to align with demo 2025-08-11 09:20:44 +08:00
zhangwei13 8c73ba8a7d add dots.ocr LICENSE AGREEMENT 2025-08-11 09:17:19 +08:00
Louis 0f5c9b68cc Delete demo/dots_ocr_colab_server.ipynb 2025-08-08 15:47:36 +01:00
Louis c4e1603f47 Add files via upload 2025-08-08 15:46:57 +01:00
Louis 6f253411fa Delete dots_ocr.ipynb at root 2025-08-08 15:45:11 +01:00
Louis 63b8fa22a9 Créé à l'aide de Colab 2025-08-08 15:32:17 +01:00
Louis e5d50e6f4b Merge pull request #1 from louisoutin/louisoutin-colab-demo 
Add Google Colab notebook demo
 2025-08-08 15:19:15 +01:00
Louis 2613af22b6 Add dots.ocr google colab notebook demo 2025-08-08 15:08:00 +01:00
zhangwei13 b195bb9b59 add NOTICE 2025-08-07 17:30:45 +08:00
zhangwei13 8a327a9c5d CPU inference 2025-08-07 16:51:10 +08:00
zhangwei13 b3bcca5ffb update wechat 2025-08-07 16:28:26 +08:00
zhangwei13 dcd3256cc7 fix clean text bug 2025-08-07 16:22:23 +08:00
zhangwei13 1bfc94c224 fix demo session caceh bug 2025-08-07 16:21:39 +08:00
Qing Yan e032665f4c Merge pull request #48 from Doge2077/master 
修复非标准图片base64格式导致图像显示错误
 2025-08-07 14:03:18 +08:00
Doge2077 3e9c068fc3 fix:image base64 std-format. 2025-08-07 10:52:18 +08:00
Qing Yan 6a5e2ba95c Merge pull request #33 from yjmm10/master 
support infer with transformer
 2025-08-05 21:19:48 +08:00
Qing Yan dbbe9d78ba Merge pull request #34 from openmartin/master 
Update parser.py open file with encoding to support windows
 2025-08-05 21:19:26 +08:00
openmartin 37b62d9b7c Update parser.py open file with encoding to support windows 2025-08-05 15:12:02 +08:00
liferecords 9d8b7e6039 support infer with transformers 
add use_hf
 2025-08-05 14:38:02 +08:00
liferecords 2a7d5e1f5a support infer with transformers 
add `--use_hf true` to use transformers，but the speed is very slower than vllm
 2025-08-05 14:18:02 +08:00
zhangwei13 ae0ca3a8be udpate wechat, fix some little bugs 2025-08-05 11:34:53 +08:00
redmoe-moutain b370ec0f0c Merge pull request #25 from LeviWeiPower/master 
support docker-compose
 2025-08-05 09:08:10 +08:00
LeviWeiPower eff6c15137 Update docker-compose.yml 
del  - CUDA_VISIBLE_DEVICES=0
 2025-08-05 00:19:09 +08:00
LeviWeiPower f52599bbca Update docker-compose.yml 
add model download comment
 2025-08-05 00:16:03 +08:00
LeviWeiPower 8b88ecbac0 Update docker-compose.yml 
support docker-compose
 2025-08-05 00:05:45 +08:00
LeviWeiPower 9a28eb9f63 Update docker-compose.yml 
support docker-compose
 2025-08-05 00:04:53 +08:00
LeviWeiPower 912e787643 support docker-compose 
support docker-compose
 2025-08-05 00:01:22 +08:00
redmoe-moutain 7be0c5e2ac Merge pull request #9 from yjmm10/support-modelscope 
Support modelscope
 2025-08-01 17:11:14 +08:00
liferecords f02e0ffd25 Update README.md 2025-08-01 16:39:02 +08:00
liferecords 1fd404be07 Update requirements.txt 2025-08-01 16:37:06 +08:00
liferecords 948f1c2a06 Update download_model.py 
download models with modelscope
 2025-08-01 16:36:19 +08:00
zhangwei13 96d06b9b15 update README 2025-07-31 16:12:40 +08:00
zhangwei13 2db2279526 update README 2025-07-31 10:21:38 +08:00
zhangwei13 5eb3cfbcf5 add blog 2025-07-31 10:07:38 +08:00
zhangwei13 444de5cf68 update README 2025-07-30 19:28:35 +08:00
zhangwei13 b58f4e1d8f update README 2025-07-30 19:17:41 +08:00
zhangwei13 be77dff22c dots.ocr release 2025-07-30 19:12:56 +08:00