"docs/examples/llm_deployment.md" did not exist on "70266ec8e2212a281ca6fdc73d0f9ccba4bfb35e"
  1. 21 May, 2025 1 commit
  2. 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
  3. 15 May, 2025 1 commit
  4. 09 May, 2025 1 commit
  5. 07 May, 2025 1 commit
  6. 02 May, 2025 1 commit
  7. 24 Apr, 2025 1 commit
  8. 17 Apr, 2025 1 commit
  9. 11 Apr, 2025 1 commit
  10. 08 Apr, 2025 1 commit
  11. 03 Apr, 2025 1 commit