Declarative MLOps: Streamlining Model Serving on Kubernetes

Declarative MLOps: Streamlining Model Serving on Kubernetes

MLOps.community via YouTube Direct link

[] Buil your own container

15 of 46

15 of 46

[] Buil your own container

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Declarative MLOps: Streamlining Model Serving on Kubernetes

Automatically move to the next video in the Classroom when playback concludes

  1. 1 [] Musical introduction to Rahul Parundekar
  2. 2 [] LLMs in Production Conference announcement
  3. 3 [] Purchase our Swag shirt!
  4. 4 [] Declarative Paradigm
  5. 5 [] Why now?
  6. 6 [] It's great for scalability
  7. 7 [] Most MLOps tools work well with K8s
  8. 8 [] Easy-deploys with tool-provided CRDs
  9. 9 [] Caveats
  10. 10 [] This talk
  11. 11 [] 3 Ways to Serve ML Models
  12. 12 [] Way 1: Serving a Model with an HTTP Endpoint
  13. 13 [] Way 2: Serving the Model with a Message Queue
  14. 14 [] Way 3: Long-running Task that Performs Batch Processing
  15. 15 [] Buil your own container
  16. 16 [] The main predictor 1/2: Singleton with load method
  17. 17 [] The main predictor 2/2: Predict
  18. 18 [] Way 1 5 steps
  19. 19 [] Way 2 2 steps
  20. 20 [] Way 3 2 steps
  21. 21 [] Tests: Sanity check for the model
  22. 22 [] Bringing it together: Entrypoint
  23. 23 [] Continuous Integration CI
  24. 24 [] Create docker-compose.yaml to make it easier for CI
  25. 25 [] On PR: Run tests with Github Actions
  26. 26 [] Branch-protection
  27. 27 [] On PR: Github Actions automatically runs our test
  28. 28 [] On PR: PRs can be then merged on approval
  29. 29 [] Container Repository
  30. 30 [] Continuous Integration CI
  31. 31 [] On merge to main
  32. 32 [] Actions that can constraint
  33. 33 [] TODO
  34. 34 [] Continuous Delivery
  35. 35 [] Argo CD
  36. 36 [] Image promotion with Kustomize
  37. 37 []
  38. 38 []
  39. 39 []
  40. 40 []
  41. 41 []
  42. 42 []
  43. 43 []
  44. 44 []
  45. 45 []
  46. 46 []

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.