t2v-transformers-models icon indicating copy to clipboard operation
t2v-transformers-models copied to clipboard

Published 20 hours ago • verified publisher icon weaviate

Adding support for running HuggingFace models on AWS Inferentia

Open zoltan-fedor opened this issue 3 years ago • 3 comments

To achieve much faster inference.

See https://huggingface.co/blog/bert-inferentia-sagemaker#1-convert-your-hugging-face-transformer-to-aws-neuron

zoltan-fedor avatar Apr 16 '22 02:04 zoltan-fedor

To avoid any confusion in the future about your contribution to Weaviate, we work with a Contributor License Agreement. If you agree, you can simply add a comment to this PR that you agree with the CLA so that we can merge.

beep boop - the SeMI bot 👋🤖

weaviate-git-bot avatar Apr 16 '22 19:04 weaviate-git-bot

I agree with the CLA.

zoltan-fedor avatar Apr 16 '22 19:04 zoltan-fedor

@zoltan-fedor – apologies for the late response and thanks for your PR! We are on it :-)

bobvanluijt avatar Jun 27 '22 15:06 bobvanluijt