GitLab

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Tzu-Ling Kan <tzulingk@nvidia.com>

Signed-off-by: Ryan Olson <rolson@nvidia.com>
Co-authored-by: Olga Andreeva <oandreeva@nvidia.com>
Co-authored-by: Ziqi Fan <ziqif@nvidia.com>
Co-authored-by: John Thompson <jothomson@nvidia.com>
Co-authored-by: Richard Huo <rihuo@nvidia.com>
Co-authored-by: Zicheng Ma <zichengm@nvidia.com>

Signed-off-by: nachiketb-nvidia <nachiketb@nvidia.com>

Signed-off-by: jthomson04 <jwillthomson19@gmail.com>

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Olga Andreeva <124622579+oandreeva-nv@users.noreply.github.com>

Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Co-authored-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Ryan Olson <ryanolson@users.noreply.github.com>

Llama 4 has a very large context length (aka n_ctx, model_max_length, max_model_len), and vllm won't start unless it can allocate enough KV cache for the entire context.

Allow passing `--context-length <N>` to `dynamo-run` to limit it so long-context models will fit.

Future todo:
- Restrict every request's `max_tokens` to below the context length. Our pre-processor should do this by setting stop_conditions.max_tokens. mistralrs engine wrapper must do it itself because it does not use the pre-processor.
- mistralrs and llamacpp currently have a hard-coded max context length if one is not provided on the command line. Change those to be the model's built-in max, read from the GGUF or tokenizer_config.json.

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.

The Python bindings use the default value for RouterMode. Previously that was Random (good), but now it became None (bad).

Remove the option and clean up the duplicate RouterMode. I was trying to avoid putting the `KV` enum in dynamo-runtime. Turns out adding those two characters gives us a healthy simplification, and restores the old default router value.

Also clean up two noisy log messages when waiting for KV routing metrics to start in worker.

Router:
```
dynamo-run in=http out=dyn://dynamo.endpoint.generate --router-mode kv
```

Worker (* N):
```
dynamo-run in=dyn://dynamo.endpoint.generate out=vllm /data/llms/Qwen/Qwen3-4B
```

You need patched vllm and the C bindings `.so`. Full docs in the updated guide: `docs/guides/dynamo_run.md`.

This gives us a pure-Rust ingress node: OpenAI compliant HTTP server + Pre-processor + KV-aware router.

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

Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>