Robin Picard

This is now available in Outlines v1. Here's the [documentation](https://dottxt-ai.github.io/outlines/latest/features/models/vllm_offline/) for the model (renamed `VLLMOffline` as we also have `VLLM` for the online server mode)

I think we have the option of keeping a single model and loader function and just treat the calls to the model differently based on whether the 2nd argument provided...

I was aware of it and thought it was intended. I'm not not too keen on putting it back as I believe it paradoxically ends up making the life of...

This has been fixed in Outlines v1. We updated the `VLMMOffline` model to use their new interface in which we provide the type and they create the logits processor on...

Hi @lm-cyber! The library has changed a lot recently since we released Outlines v1. I believe it makes handling the subject of your PR either though! I think what we...

Closing it as the issue has been treated by #1672

Hi @omer-dtc. Thanks for opening a PR! We're currently working on updating the documentation of the [v.1.0 branch](https://github.com/dottxt-ai/outlines/tree/v1.0) that should be merged into main soon. So I don't think it...

Thanks for the detailed issue! We're working on adding explicit support for reasoning models, this example will surely be very useful to understand the problem and find a way of...

Closing the issue as removing the CFGLogitsProcessor (#1700) reduced the time it takes to run the tests by more than half.

Awesome! I think the most useful part is accepting a url for images, but then it means such images could not be used for local models, so there is a...