1. 08 Jul, 2025 2 commits
  2. 07 Jul, 2025 1 commit
  3. 29 May, 2025 1 commit
  4. 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
  5. 29 Apr, 2025 1 commit
    • Graham King's avatar
      chore: Split PushRouter from Client (#817) · a1a10365
      Graham King authored
      In a distributed system we don't know if the remote workers need pre-processing done ingress-side or not. Previously Client required us to decide this before discovering the remote endpoints, which was fine because pre-processing was worker-side.
      
      As part of moving pre-processing back to ingress-side we need to split this into two steps:
      - Client discovers the endpoints, and (later PR) will fetch their Model Deployment Card.
      - PushRouter will use the Model Deployment Card to decide if they need pre-processing or not, which affects the types of the generic parameters.
      
      Part of #743
      a1a10365
  6. 11 Apr, 2025 1 commit
  7. 04 Apr, 2025 1 commit
    • Graham King's avatar
      feat: Python decorator dynamo_worker takes optional `static` parameter without etcd (#494) · 88ad3425
      Graham King authored
      Adds `@dynamo_worker(static = True)` to create a static worker which has a predictable name and hence does not require discovery or `etcd` to be running. There can only be a single static worker per namespace / component / endpoint trio.
      
      This contrasts with the default dynamic `dynamo_worker` endpoints we have now, which get a unique random name (based on namespace/component/endpoint), and are discovered by ingress components using etcd.
      
      Also change the hello_world example to use `dynamo_worker(static = True)` so that it is exercised and demonstrated somewhere.
      
      For NIM.
      88ad3425
  8. 02 Apr, 2025 1 commit
  9. 31 Mar, 2025 1 commit
  10. 19 Mar, 2025 1 commit
    • Graham King's avatar
      chore: Don't depend on openssl (#292) · 7c3fd5c9
      Graham King authored
      This makes the Rust parts all use ring / rustls library instead of local install of openssl. It's a step on the journey to being statically linked.
      
      Pieces:
      - `tokenizers` and `mistralrs` now support rustls (mistralrs by default, tokenizers with feature flag).
      - Move shared dependencies up into workspace
      - New `rand` crate has some renames for future rust
      - Ensure the dependency doesn't creep back in by enforcing it with cargo deny.
      7c3fd5c9
  11. 17 Mar, 2025 1 commit
  12. 14 Mar, 2025 1 commit
  13. 12 Mar, 2025 1 commit
  14. 11 Mar, 2025 1 commit
  15. 08 Mar, 2025 1 commit
  16. 07 Mar, 2025 3 commits