GitLab

Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Ishan Dhanani <ishandhanani@gmail.com>
Co-authored-by: Sean SH Choi <sechoi@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>

Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

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>

Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>

Signed-off-by: Biswa Panda <biswa.panda@gmail.com>

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

Move much of what was in the `dynamo-run` crate into `dynamo-llm` so that everyone can use it.

Example usage:

1. Create a `LocalModel`:

```
    let local_model = LocalModelBuilder::default()
	.model_path("Qwen/Qwen3-0.6B")
	.http_port(8080)
	.build().await?;
```

2. Make an engine:

```
    let engine_config = EngineConfig::StaticFull {
	engine: dynamo_engine_mistralrs::make_engine(&local_model).await?,
	model: Box::new(local_model),
    };
```

3. Connect it to an input and run it

```
    dynamo_llm::entrypoint::input::run_input(Input::Http, runtime, engine_config).await?;
```

For https://github.com/ai-dynamo/dynamo/issues/1647

Code Rabbit summary, thanks:
  * Introduced a flexible builder pattern for local model configuration, allowing advanced customization and easier initialization.
  * Added new input modes and unified input handling, supporting interactive chat, HTTP server, batch file, and distributed endpoint modes.
  * Centralized engine configuration and routing, enabling more extensible and maintainable engine management.
  * Simplified and modularized the codebase by moving input and engine logic into dedicated modules.
  * Replaced direct model construction with an asynchronous builder for improved clarity and extensibility.
  * Streamlined configuration and validation for flags and router settings.
  * Added validation to prevent incompatible input and output combinations in endpoint and dynamic modes.

It was confusing to have two names for one type.

This tidy up started in #1064 , is now complete.

- 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.

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.

Implements OpenAI embeddings (interface only).

- Adds ModelType::Embedding
- Adds OpenAI embedding request/response structs
- Adds support for embedding model discovery

Each namespace is for a single pipeline, so a component must be model-unique. The means we can have several components with the same name running the same model (data parallel), their traffic will be routed according to `--router-mode`, but we cannot have several components with the same name running different models.

Add an `ensure_unique` check to prevent that happening.

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.

vllm and sglang are now the sub-process engines from #954

Also updated docs on doing vllm and sglang multi-gpu (tensor parallel) and multi-node (pipeline parallel).

Adding this to a Python script makes it register on the network so that `dynamo-run` can discover it and send it requests:
```
from dynamo.llm import register_llm

MODEL = "Qwen/Qwen2.5-0.5B-Instruct"
await register_llm(endpoint, MODEL, 3)
```

Full vllm example, with pre-processing in dynamo:
- `dynamo-run in=text out=dyn://dynamo.backend.generate`
- `cd lib/bindings/python/examples/hello_world`
- `python server_vllm.py`

This builds on top of the work to move pre-processor to ingress side. It means we can decouple Rust and Python using NATS as the bus.

The `register_llm` call does this:

- Download the model from HF if necessary
- Load the model deployment card from the HF folder or extract from GGUF
- Push the tokenizer config etc into NATS object store so ingress can access it from a different machine
- Publish the model deployment card to ETCD