Charlie Masters

@AIasd Reading through the enhancement it seems like it was merged to master then the 0.11.0 branch was deleted. However from what I can see there is is not GPU...

Bumping as same here running to download 7b.

**Description of the System:** Unfortunately, I do not own the model, it is a TAPAS model from the Transformers library [Tapas Documentation](https://huggingface.co/docs/transformers/model_doc/tapas), so I can't edit its implementation. For reproducibility,...

I ended up just regressing to wrapping the model in a fast API server since the performance bottleneck isn't huge, but still, for future use cases this may still be...

Bumping this. same issue

@kaykyr @danielhanchen @tohrnii You guys open to some collaboration on this? I think I just my Phi2 implementation done (big touch wood) so I'm happy to take a look

@kaykyr funny you mention that- I've got almost the exact same setup! I'm going to be very sad when they deprecate the SLI bridge as cuda supported hardware

hi @tranlm, I'm cracking through it slowly but surely!

Addresses #85

@danielhanchen I've implemented the ReLU and LayerNorm kernels for the model and added some test coverage around their closeness. Mind having a review when you get a min? ty!