Support for Falcon-7B / 40B models

[sujithjoseph]

It would be great, if you can add support for Falcon models as well! Does it support onnx models today?

[WoosukKwon]

Currently, vLLM does not support ONNX models. Supporting Falcon is on our roadmap. Thanks for your suggestion.

[MotzWanted]

@WoosukKwon When do you anticipate adding support for Falcon to vLLM?

[WoosukKwon]

@MotzWanted I'm working on it now. I think we can add less-optimized version of Falcon (MQA replaced by MHA) quickly (within a few days) and then develop kernels to make the model actually use MQA.

[emphasis10]

I'm waiting for supporting Falcon families, too. Thanks a lot for your works.

[HSQ79815]

great, thanks

[teopapad92]

thanks, looking forward to it