Skip to content

Conversation

@simon-mo
Copy link
Collaborator

This should fix #2661

Copy link
Member

@zhuohan123 zhuohan123 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! Thanks for the work!

requirements = f.read().strip().split("\n")
elif _is_neuron():
with open(get_path("requirements-neuron.txt")) as f:
requirements = f.read().strip().split("\n")
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add an else statement here and raise an error in it?

setup.py Outdated

def _is_cuda() -> bool:
return (torch.version.cuda is not None) and not _is_neuron()
return shutil.which("neuron-ls") is not None

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just to let you know, I tried implementing just this line and it doesn't work on an AWS AMI as the neuron-ls package is installed, but if you're not on a neuron device then it still fails. What worked for me was to just change the errors caught on line 39 to include 'subprocess.CalledProcessError'.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! updated my PR to reflect that

@simon-mo simon-mo merged commit 6b78837 into vllm-project:main Mar 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Fail to use ``pip install -e .''

3 participants