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

Closed dacorvo closed 2 months ago

dacorvo commented 2 months ago

What does this PR do?

This bumps the NeuronX TGI router version to 2.0.1, using an Apache 2.0 License.