huggingface / optimum-neuron

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.

Apache License 2.0

176 stars 51 forks source link

Do not copy local checkpoint #630

Closed dacorvo closed 2 weeks ago

dacorvo commented 2 weeks ago

What does this PR do?

This avoids a redundant copy when a model is exported from a local path. This is made possible by the fact that we don;t need to split the model weights anymore.

HuggingFaceDocBuilderDev commented 2 weeks ago

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.