Commits · 6ffd20a81c09dcf9576cbcf8575c72dd27bc68f1 · OpenDAS / dynamo

Olga Andreeva authored Sep 03, 2025

refactor: Split ModelType to ModelInput for request and response type; ModelType for the supported workloads (#2714)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Guan Luo <gluo@nvidia.com>
Co-authored-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>

27fad26f

22 Aug, 2025 1 commit
- chore(llm): Rename protocols::Endpoint to EndpointId (#2615) · 6a358f7c
  Graham King authored Aug 22, 2025
  
  6a358f7c
14 Aug, 2025 1 commit
- feat: add RuntimeConfig to ModelEntry (#2311) · d0a63635
  Jorge António authored Aug 14, 2025
```
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
```
  d0a63635
11 Jun, 2025 1 commit
- refactor: move kv store to runtime (#1459) · 08355da6
  Ryan Olson authored Jun 11, 2025
  
  08355da6
21 May, 2025 2 commits
- fix(llmctl): Use ModelWatcher instead of direct etcd operations (#1150) · 3e8e38a9
  Graham King authored May 21, 2025
  
  3e8e38a9
- chore: Fix model removal on instance stop, refactor discovery (#1142) · b520bf44
  Graham King authored May 21, 2025
```
- Stop advertising a model when it's last instance stops. Previously was when any instance stops.
- Faster locks on model manager.
- Move discovery code out of http, as it is used by all inputs.
```
  b520bf44