search

InftyAI / llmaz

☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!
Apache License 2.0
30 stars 10 forks source link

Downsize model-loader image #179

Closed qinguoyi closed 1 month ago

qinguoyi commented 1 month ago

What this PR does / why we need it

Downsize model-loader image

Which issue(s) this PR fixes

Fixes #

Special notes for your reviewer

  1. We use a staged build and using the new dockerfile we see the image reduced from 470MB to 155MB.
image
  1. We tested the old and new images and found that they can all start normally. （1）the new image image

    (2) the old image

    image

Does this PR introduce a user-facing change?

kerthcet commented 1 month ago

Awesome, thanks for this!

/kind cleanup /lgtm /approve