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

Upgrade Neuron SDK to 2.18.0 and TGI to 1.4.5 (fix) #548

Closed davidshtian closed 3 months ago

davidshtian commented 3 months ago

What does this PR do?

Fixes # (issue) Upgrade the version will fix the issue.

Before submitting

dacorvo commented 3 months ago

Thank you for this pull-request, which is almost perfect except it does not update optimum-neuron itself. Please see our own pull-request to bump AWS Neuron SDK version.

dacorvo commented 3 months ago

See #547