awslabs / llm-hosting-container

Large Language Model Hosting Container
Apache License 2.0
74 stars 26 forks source link

Add Neuronx TGI 0.0.22 #71

Closed philschmid closed 3 months ago

philschmid commented 4 months ago

What this PR do?

This PR adds a new TGI neuron version to properly support Llama 3 instruct on inferentia.

amzn-choeric commented 4 months ago

AWS CodeBuild CI Report

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

amzn-choeric commented 4 months ago

AWS CodeBuild CI Report

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

amzn-choeric commented 4 months ago

AWS CodeBuild CI Report

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository