Originally posted by albertmkc June 16, 2024
I used the command as suggested on Ollama.com to run locally in Windows Docker with CUDA, Ollama separately installed. Successful a month ago with my PC with RTX3090 and inference with GPU with no problem.
Today, I accidentally deleted the container and using the same image pulled before, then it prompts me NVIDIA driver is not available.
I have reinstalled everything, e.g. Nvidia drivers from website, docker 4.31 (latest released), and even the entire system, it is still not working. I believe it had updated something from the PYTorch library but I have no Python/ Docker/ Linux knowledge to fix it.
Can someone help me out on this? Thanks!
2024-06-16 06:24:26 Traceback (most recent call last):
2024-06-16 06:24:26 File "/usr/local/bin/uvicorn", line 8, in <module>
2024-06-16 06:24:26 sys.exit(main())
2024-06-16 06:24:26 ^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1157, in __call__
2024-06-16 06:24:26 return self.main(*args, **kwargs)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1078, in main
2024-06-16 06:24:26 rv = self.invoke(ctx)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1434, in invoke
2024-06-16 06:24:26 return ctx.invoke(self.callback, **ctx.params)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 783, in invoke
2024-06-16 06:24:26 return __callback(*args, **kwargs)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/main.py", line 410, in main
2024-06-16 06:24:26 run(
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/main.py", line 578, in run
2024-06-16 06:24:26 server.run()
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 61, in run
2024-06-16 06:24:26 return asyncio.run(self.serve(sockets=sockets))
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/asyncio/runners.py", line 190, in run
2024-06-16 06:24:26 return runner.run(main)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run
2024-06-16 06:24:26 return self._loop.run_until_complete(task)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 68, in serve
2024-06-16 06:24:26 config.load()
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/config.py", line 473, in load
2024-06-16 06:24:26 self.loaded_app = import_from_string(self.app)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/importer.py", line 21, in import_from_string
2024-06-16 06:24:26 module = importlib.import_module(module_str)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/importlib/__init__.py", line 126, in import_module
2024-06-16 06:24:26 return _bootstrap._gcd_import(name[level:], package, level)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
2024-06-16 06:24:26 File "<frozen importlib._bootstrap_external>", line 940, in exec_module
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
2024-06-16 06:24:26 File "/app/backend/main.py", line 43, in <module>
2024-06-16 06:24:26 from apps.rag.main import app as rag_app
2024-06-16 06:24:26 File "/app/backend/apps/rag/main.py", line 207, in <module>
2024-06-16 06:24:26 update_embedding_model(
2024-06-16 06:24:26 File "/app/backend/apps/rag/main.py", line 184, in update_embedding_model
2024-06-16 06:24:26 app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/sentence_transformers/SentenceTransformer.py", line 221, in __init__
2024-06-16 06:24:26 self.to(device)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1173, in to
2024-06-16 06:24:26 return self._apply(convert)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 [Previous line repeated 1 more time]
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 804, in _apply
2024-06-16 06:24:26 param_applied = fn(param)
2024-06-16 06:24:26 ^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1159, in convert
2024-06-16 06:24:26 return t.to(
2024-06-16 06:24:26 ^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/cuda/__init__.py", line 293, in _lazy_init
2024-06-16 06:24:26 torch._C._cuda_init()
2024-06-16 06:24:26 RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
```</div>
Originally created by @albertmkc on GitHub (Jun 16, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3216
### Discussed in https://github.com/open-webui/open-webui/discussions/3213
<div type='discussions-op-text'>
<sup>Originally posted by **albertmkc** June 16, 2024</sup>
I used the command as suggested on Ollama.com to run locally in Windows Docker with CUDA, Ollama separately installed. Successful a month ago with my PC with RTX3090 and inference with GPU with no problem.
Today, I accidentally deleted the container and using the same image pulled before, then it prompts me NVIDIA driver is not available.
I have reinstalled everything, e.g. Nvidia drivers from website, docker 4.31 (latest released), and even the entire system, it is still not working. I believe it had updated something from the PYTorch library but I have no Python/ Docker/ Linux knowledge to fix it.
Can someone help me out on this? Thanks!
```
2024-06-16 06:24:26 Traceback (most recent call last):
2024-06-16 06:24:26 File "/usr/local/bin/uvicorn", line 8, in <module>
2024-06-16 06:24:26 sys.exit(main())
2024-06-16 06:24:26 ^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1157, in __call__
2024-06-16 06:24:26 return self.main(*args, **kwargs)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1078, in main
2024-06-16 06:24:26 rv = self.invoke(ctx)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 1434, in invoke
2024-06-16 06:24:26 return ctx.invoke(self.callback, **ctx.params)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/click/core.py", line 783, in invoke
2024-06-16 06:24:26 return __callback(*args, **kwargs)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/main.py", line 410, in main
2024-06-16 06:24:26 run(
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/main.py", line 578, in run
2024-06-16 06:24:26 server.run()
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 61, in run
2024-06-16 06:24:26 return asyncio.run(self.serve(sockets=sockets))
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/asyncio/runners.py", line 190, in run
2024-06-16 06:24:26 return runner.run(main)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run
2024-06-16 06:24:26 return self._loop.run_until_complete(task)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 68, in serve
2024-06-16 06:24:26 config.load()
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/config.py", line 473, in load
2024-06-16 06:24:26 self.loaded_app = import_from_string(self.app)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/uvicorn/importer.py", line 21, in import_from_string
2024-06-16 06:24:26 module = importlib.import_module(module_str)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/importlib/__init__.py", line 126, in import_module
2024-06-16 06:24:26 return _bootstrap._gcd_import(name[level:], package, level)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
2024-06-16 06:24:26 File "<frozen importlib._bootstrap_external>", line 940, in exec_module
2024-06-16 06:24:26 File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
2024-06-16 06:24:26 File "/app/backend/main.py", line 43, in <module>
2024-06-16 06:24:26 from apps.rag.main import app as rag_app
2024-06-16 06:24:26 File "/app/backend/apps/rag/main.py", line 207, in <module>
2024-06-16 06:24:26 update_embedding_model(
2024-06-16 06:24:26 File "/app/backend/apps/rag/main.py", line 184, in update_embedding_model
2024-06-16 06:24:26 app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/sentence_transformers/SentenceTransformer.py", line 221, in __init__
2024-06-16 06:24:26 self.to(device)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1173, in to
2024-06-16 06:24:26 return self._apply(convert)
2024-06-16 06:24:26 ^^^^^^^^^^^^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 779, in _apply
2024-06-16 06:24:26 module._apply(fn)
2024-06-16 06:24:26 [Previous line repeated 1 more time]
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 804, in _apply
2024-06-16 06:24:26 param_applied = fn(param)
2024-06-16 06:24:26 ^^^^^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1159, in convert
2024-06-16 06:24:26 return t.to(
2024-06-16 06:24:26 ^^^^^
2024-06-16 06:24:26 File "/usr/local/lib/python3.11/site-packages/torch/cuda/__init__.py", line 293, in _lazy_init
2024-06-16 06:24:26 torch._C._cuda_init()
2024-06-16 06:24:26 RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
```</div>
<!-- gh-comment-id:2171746669 -->
@pkeffect commented on GitHub (Jun 16, 2024):
Did you also install
https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
This is needed for Docker to talk to your gpu.
Edited for correct link.
Thanks! Eventually it was the docker version which is not compatible. After upgrade (requires reinstall of SD) it is working now! Thanks for support.
<!-- gh-comment-id:2212316006 -->
@albertmkc commented on GitHub (Jul 7, 2024):
Thanks! Eventually it was the docker version which is not compatible. After upgrade (requires reinstall of SD) it is working now! Thanks for support.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @albertmkc on GitHub (Jun 16, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3216
Discussed in https://github.com/open-webui/open-webui/discussions/3213
Originally posted by albertmkc June 16, 2024
I used the command as suggested on Ollama.com to run locally in Windows Docker with CUDA, Ollama separately installed. Successful a month ago with my PC with RTX3090 and inference with GPU with no problem.
Today, I accidentally deleted the container and using the same image pulled before, then it prompts me NVIDIA driver is not available.
I have reinstalled everything, e.g. Nvidia drivers from website, docker 4.31 (latest released), and even the entire system, it is still not working. I believe it had updated something from the PYTorch library but I have no Python/ Docker/ Linux knowledge to fix it.
Can someone help me out on this? Thanks!
@pkeffect commented on GitHub (Jun 16, 2024):
Did you also install
https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
This is needed for Docker to talk to your gpu.
Edited for correct link.
@tjbck commented on GitHub (Jun 16, 2024):
#2527
@albertmkc commented on GitHub (Jul 7, 2024):
Thanks! Eventually it was the docker version which is not compatible. After upgrade (requires reinstall of SD) it is working now! Thanks for support.