Skip to content

Instantly share code, notes, and snippets.

@caleb-kaiser
Created November 6, 2019 23:24
Show Gist options
  • Save caleb-kaiser/532c5ccd89ffe0b4a513a777eebe1a1a to your computer and use it in GitHub Desktop.
Save caleb-kaiser/532c5ccd89ffe0b4a513a777eebe1a1a to your computer and use it in GitHub Desktop.
# cortex.yaml
- kind: deployment
name: text
- kind: api
name: generator
predictor:
path: predictor.py
metadata:
num_words: 50 # generate 50 words per request
device: cuda # run on GPU
compute:
gpu: 1
cpu: 1
@ariel-frischer
Copy link

Thanks for sharing this script but it seems old, getting some errors trying to deploy, like: error: cortex.yaml: text: kind: invalid value (got "deployment", must be "RealtimeAPI", "BatchAPI", or "TrafficSplitter"), after fixing that I got: error: cortex.yaml: dgpt-2 (RealtimeAPI): predictor: must be defined. Can this be updated?

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