1. 02 Jun, 2025 1 commit
  2. 31 May, 2025 1 commit
  3. 30 May, 2025 2 commits
  4. 29 May, 2025 1 commit
  5. 28 May, 2025 1 commit
  6. 27 May, 2025 1 commit
  7. 22 May, 2025 2 commits
  8. 21 May, 2025 2 commits
  9. 20 May, 2025 2 commits
  10. 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
  11. 15 May, 2025 1 commit
  12. 12 May, 2025 1 commit
  13. 09 May, 2025 1 commit
  14. 08 May, 2025 2 commits
  15. 07 May, 2025 3 commits
  16. 06 May, 2025 2 commits
  17. 05 May, 2025 2 commits
  18. 01 May, 2025 1 commit
  19. 30 Apr, 2025 2 commits
  20. 29 Apr, 2025 1 commit
  21. 28 Apr, 2025 2 commits
  22. 26 Apr, 2025 1 commit
  23. 25 Apr, 2025 5 commits
  24. 24 Apr, 2025 1 commit
  25. 23 Apr, 2025 1 commit