[Cache Request] stabilityai/sdxl-turbo

#62

by S1m0neAI - opened Apr 22

Discussion

S1m0neAI

Apr 22

Please add the following model to the neuron cache

Jingya

AWS Inferentia and Trainium org Apr 22

Hi @qkasper0, although the cache of sdxl models is now supported by optimum neuron, there is a recent regression in the weight/neff separation since neuron SDK 2.18.0 which is mandatory for our caching mechanism. The Annapurna team is fixing it, Optimum team will add the cache as soon as the issue is fixed: https://github.com/aws-neuron/aws-neuron-sdk/issues/859.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment