- 08 Jul, 2025 2 commits
-
-
Yan Ru Pei authored
Signed-off-by:
Yan Ru Pei <yanrpei@gmail.com> Co-authored-by:
Alec <35311602+alec-flowers@users.noreply.github.com>
-
Keiven C authored
Co-authored-by:Keiven Chang <keivenchang@users.noreply.github.com>
-
- 07 Jul, 2025 1 commit
-
-
jain-ria authored
Signed-off-by:
jain-ria <riajain@NVIDIA.com> Co-authored-by:
Alec <35311602+alec-flowers@users.noreply.github.com>
-
- 29 May, 2025 1 commit
-
-
Alec authored
-
- 19 May, 2025 1 commit
-
-
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.
-
- 29 Apr, 2025 1 commit
-
-
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
-
- 11 Apr, 2025 1 commit
-
-
Ryan McCormick authored
- Replace custom StatsWithData object with library-defined Metrics object - Update parsing logic to account for change to Metrics.decode()
-
- 04 Apr, 2025 1 commit
-
-
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.
-
- 02 Apr, 2025 1 commit
-
-
Ryan Olson authored
-
- 31 Mar, 2025 1 commit
-
-
Ryan Olson authored
-
- 19 Mar, 2025 1 commit
-
-
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.
-
- 17 Mar, 2025 1 commit
-
-
Ryan McCormick authored
-
- 14 Mar, 2025 1 commit
-
-
Ryan McCormick authored
-
- 12 Mar, 2025 1 commit
-
-
Ryan McCormick authored
-
- 11 Mar, 2025 1 commit
-
-
Alec authored
-
- 08 Mar, 2025 1 commit
-
-
Neelay Shah authored
Co-authored-by:Biswa Panda <biswa.panda@gmail.com>
-
- 07 Mar, 2025 3 commits
-
-
Ryan McCormick authored
-
Ryan McCormick authored
Replaces hard-coded "kv-hit-rate" string in multiple places with KV_HIT_RATE_SUBJECT constant in lib/llm.
-
Neelay Shah authored
-