1. 04 Jun, 2025 1 commit
  2. 03 Jun, 2025 1 commit
  3. 30 May, 2025 1 commit
  4. 29 May, 2025 1 commit
  5. 21 May, 2025 1 commit
  6. 20 May, 2025 1 commit
  7. 19 May, 2025 1 commit
    • Graham King's avatar
      feat: Support multiple models on single ingress node (#1127) · aeb79e62
      Graham King authored
      We can now do this:
      
      - Node 1:
      
      ```
      dynamo-run in=http out=dyn
      ```
      
      - Node 2 and 3, two instances of component 'backend' in the nemotron_ultra pipeline:
      
      ```
      dynamo-run in=dyn://nemotron_ultra.backend.generate out=vllm /data/models/NemotronUltra
      ```
      
      - Node 4 and 5, two instances of the 'backend' component in nemotron_super pipeline:
      
      ```
      dynamo-run in=dyn://nemotron_super.backend.generate out=vllm /data/models/NemotronSuper
      ```
      
      The ingress node will discover all four instances and route correctly. We have been planning for this for a long time now.
      
      As part of this auto-discovery is now always `out=dyn`, with no extra URL parts. Previously it could only route to a single pipeline.
      
      Also:
      - Refactor endpoint / instance naming now that I understand them
      - Fix removing models when their instance stops.
      aeb79e62
  8. 15 May, 2025 1 commit
  9. 12 May, 2025 1 commit
  10. 09 May, 2025 1 commit
  11. 08 May, 2025 2 commits
  12. 07 May, 2025 2 commits
  13. 05 May, 2025 1 commit
  14. 01 May, 2025 1 commit
  15. 30 Apr, 2025 1 commit
  16. 28 Apr, 2025 1 commit
  17. 26 Apr, 2025 1 commit
  18. 25 Apr, 2025 2 commits
  19. 21 Apr, 2025 1 commit
  20. 18 Apr, 2025 1 commit
  21. 17 Apr, 2025 1 commit
  22. 15 Apr, 2025 1 commit
  23. 14 Apr, 2025 1 commit
  24. 12 Apr, 2025 1 commit
  25. 11 Apr, 2025 1 commit
  26. 10 Apr, 2025 2 commits
  27. 09 Apr, 2025 1 commit
  28. 07 Apr, 2025 1 commit
  29. 04 Apr, 2025 1 commit
  30. 31 Mar, 2025 1 commit
  31. 26 Mar, 2025 2 commits
  32. 24 Mar, 2025 1 commit
  33. 20 Mar, 2025 1 commit
  34. 19 Mar, 2025 2 commits