ImportError: libcudnn.so.8: cannot open shared object file: No such file or directory #778
Unanswered
Xxcoincoin
asked this question in
Q&A
Replies: 1 comment
-
Error: connect ECONNREFUSED 127.0.0.1:3000 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello everyone, I installed OpenDevin on WSL2. I followed the tutorial in LOCAL_LLM_GUIDE.md
So launching in a cuda environment (od)
-make build
-modification of the configuration file
-make run: starts, but error
-make start-backend: not working
I have those errors :
ab@DESKTOP-6C3GB46:~/OpenDevin$ make run Running the app... /bin/sh: 1: [: unexpected operator make[1]: Entering directory '/home/ab/OpenDevin' Starting backend... make[1]: Entering directory '/home/ab/OpenDevin' Starting frontend... [...] ImportError: libcudnn.so.8: cannot open shared object file: No such file or directory
[...]
8:28:57 PM [vite] ws proxy error:
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /litellm-models
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /default-model
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /litellm-agents
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /litellm-models
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /default-model
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
8:28:57 PM [vite] http proxy error: /litellm-agents
Error: connect ECONNREFUSED 127.0.0.1:3000
at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16)
`
For the libcudnn error i have installed inside my conda env pip install torch => did not work / same error
Installed cuDNN with the nvidia installer (https://developer.nvidia.com/cudnn-downloads?target_os=Linux&target_arch=x86_64&Distribution=Ubuntu&target_version=22.04&target_type=deb_network) => same error...
I have no clue on what's going on, do you have some ideas ?
Thanks a lot guys !
Beta Was this translation helpful? Give feedback.
All reactions