Skip to content

Conversation

@ovgolovin
Copy link

This change creates intermediate docker image layers with dependencies.
This will leverage docker layer cache when dependencies haven't changed from previous image build. This incredibly improves docker image build times for local development.
Is also enables image consumers to reuse heavy dependency docker image layers when they pull image updates.
Also, using cache mount reduced GPU image size (output from dive tool):

  • before:
│ Image Details ├────────────────────────────────────────────────
                                                                 
Image name: onerahmet/openai-whisper-asr-webservice:latest-gpu   
Total Image size: 15 GB                                          
Potential wasted space: 7.6 MB                                   
Image efficiency score: 99 %                                     
  • after:
│ Image Details ├──────────────
                               
Image name: 5211cdf6a3c4       
Total Image size: 7.9 GB       
Potential wasted space: 14 MB  
Image efficiency score: 99 %   

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