Sameen Islam

Looking forward to MPS support!

For the time being, for those on Apple Silicon, who wants to get unblocked asap: you can use [MLX](https://github.com/ml-explore/mlx) to run HuggingFace models locally with GPU and shared memory architecture...

The issue still exists as of writing this comment: ````python import langchain print(langchain.__version__) >>> 0.1.9 import langchain_community print(langchain_community.__version__) >>> 0.0.21 ```` I encountered the issue when doing the following operation...

I came here looking for a way to profile memory usage in my Metaflow pipeline. Since this approach didn't work for me, I adopted another way to profile memory for...

I can't believe this feature is not available, it would really take the usability to another level.