Skip to content

Conversation

@RobMulla
Copy link

This pull request builds off of the existing inference/vLLM recepies and introduces an alternate workflow for running the TPU recipes using docker-compose and make.

The goal of this change is to improve the user experience by making the recipes easier to use without needing to copy/paste the docker commands. It also allows for the variables that a use might want to set to be configured in a .env file so they can manage their state.

These can be put alongside the existing recepies and won't impact their functionality.

The key changes are:

  • A docker-compose directory has been added with a new set of recipes.
  • Each recipe now includes a Makefile and a docker-compose.yml file, allowing users to run the recipes with simple commands like make setup, make up, and make benchmark.

I believe this new workflow will make the recipes more accessible and easier to use, especially for those who are new to the platform. I'm happy to receive any feedback or suggestions for improvement.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant