Giters

aws / deep-learning-containers

AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.

Home Page:https://docs.aws.amazon.com/deep-learning-containers/latest/devguide/deep-learning-containers-images.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[huggingface_pytorch_neuronx] Release Inference Image for PyTorch 1.13.1 - Transformers 4.33.1 - Neuron SDK 2.14.1

JingyaHuang opened this issue · comments

commented

Overview for Inference DLCs to update

huggingface_pytorch_neuronx

Dependencies versions:

  • transformers: 4.33.1
  • torch: 1.13.1
  • aws-neuron-sdk: 2.14.1
  • optimum-neuron: 0.0.12
  • Inference - Neuronx

cc. @arjkesh @shantanutrip

commented

Close as will skip neuron 2.14 and bump directly to 2.15 for the inference as well. neuron 2.15 hf pt inf DLC here: https://github.com/aws/deep-learning-containers/releases/tag/v1.0-hf-4.34.1-pt-1.13.1-inf-neuronx-sdk2.15.0-py310 .