-
-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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]: wheel size exceeds 200MB #6647
Comments
which commit? |
I would assume this happens when you add more version to the cuda supported arch list. |
@youkaichao latest commit 89c1c6a DOCKER_BUILDKIT=1 docker build . --target vllm-openai --tag vllm/vllm-openai |
the reason might be that your building environment is different from ci. the ci wheel size check passed. |
my environment is a pretty standard A10 and H100 Ubuntu20/22 |
if you build wheel for your private usage, you can just remove that wheel size check. we have the limit because we need to upload it to pypi . |
I'm not building it for private use. I only ran docker build. I don't think a normal docker build should fail because of that |
I am building on A10.4 Did someone figure out other than removing this check? |
Thanks |
Your current environment
🐛 Describe the bug
Seems like the main branch of vLLM is oversized, which is crashing the docker build process :/
The text was updated successfully, but these errors were encountered: