-
Notifications
You must be signed in to change notification settings - Fork 252
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] got error when pip install. docker img works though, python ver3.11 #1633
Comments
@fyxc hi, can you install mmengine |
Same problem, and here is my output:
|
@IcyFeather233 Hi, sorry about that. lmdeploy does not support MacOS. |
I tried on windows, but got the same problem
TorchVision 0.17.2+cpu |
got the same problem with pip install lmdeploy after upgrade to cuda12, is that because the py ver doesn't match? my current py ver is 3.12.2
TorchVision 0.18.0+cu121 |
@fyxc hi, this time your env shows it is cuda12.1 yet last time it is cuda11.8. Anyway, just for cuda11.x you should download whl from github release pages and for cuda12.x you could directly run
|
yeah, that's what I mean. pip install lmdeploy still doesn't work with cuda 12.1 |
@fyxc hi, use python from 3.8.x to 3.11.x. |
Checklist
Describe the bug
Note: you may need to restart the kernel to use updated packages.
ERROR: Could not find a version that satisfies the requirement lmdeploy (from versions: none)
ERROR: No matching distribution found for lmdeploy
Reproduction
pip install lmdeploy
Environment
Error traceback
No response
The text was updated successfully, but these errors were encountered: