Skip to content

Document the /v1/models endpoint #42588

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.

Sign up for GitHub

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

Open
LysandreJik wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Document the /v1/models endpoint #42588

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/source/en/serving.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,6 +413,17 @@ For example, to enable 4-bit quantization with bitsandbytes, you need to pass ad
transformers serve --quantization bnb-4bit
```

### Available models

The `/v1/models` endpoint scans your local cache for generative models. It checks for LLMs as well as VLMs.
The easiest way to download models to your cache is with the `hf download` command:
Copy link
Contributor

@Wauplin Wauplin Dec 3, 2025

Choose a reason for hiding this comment

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

Suggested change
The easiest way to download models to your cache is with the `hf download` command:
The easiest way to download models to your cache is with the `transformers download` command:


```shell
hf download <model_id>
Copy link
Member Author

@LysandreJik LysandreJik Dec 3, 2025

Choose a reason for hiding this comment

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

Actually this will download all the files (even "original" files), so there is probably a better way

Copy link
Member Author

@LysandreJik LysandreJik Dec 3, 2025

Choose a reason for hiding this comment

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

Maybe it would make sense to expose a utility that would only download the transformers-specific files

Copy link
Contributor

@Wauplin Wauplin Dec 3, 2025

Choose a reason for hiding this comment

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

do you mean something like transformers download ? If only it existed... 😛

Image

Copy link
Contributor

@Wauplin Wauplin Dec 3, 2025

Choose a reason for hiding this comment

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

Suggested change
hf download <model_id>
transformers download <model_id>

```

As long as it's a transformers-compatible LLM/VLM, it will now show up under `/v1/models`
Copy link
Contributor

@Wauplin Wauplin Dec 3, 2025

Choose a reason for hiding this comment

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

Suggested change
As long as it's a transformers-compatible LLM/VLM, it will now show up under `/v1/models`
Once downloaded, the model will show up under `/v1/models`.


### Performance tips

- Use an efficient attention backend when available:
Expand Down