[Bug]: HFValidation

[TamKez]

Your current environment

Hi, I'm trying to run vllm while loading the model from a s3 compatible storage.

Using the official image tag v0.6.6

I have defined following env vars:
AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY
AWS_ENDPOINT_URL
AWS_EC2_METADATA_DISABLED=true
RUNAI_STREAMER_S3_ENDPOINT
RUNAI_STREAMER_S3_USE_VIRTUAL_ADDRESSING=0

🐛 Describe the bug

I'm running the following command:
vllm serve s3://vllm-phi35 --load-format runai_streamer

And I get the following error:

huggingface_hub.errors/HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/tmp/tmp8px3pe24' . Use `repo_type` argument if needed.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[JaheimLee]

I also encountered this issue while loading a local model

[noa-neria]

This issue is resolved in latest version of vllm

version 0.6.6 contains a bug which was fixed here
In 0.6.6 the only path pattern that works is s3://bucket/dir/

In 0.6.6 a path which contains only a bucket such as s3://vllm-phi35 will fail

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!