GitLab

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

Signed-off-by: Tushar Sharma <tusharma@nvidia.com>

Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>

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

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

Signed-off-by: Chi McIsaac <chixie.mcisaac@gmail.com>

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

Changing the chat completions response objects from structs to types of dynamo_async_openai

Implement aggregator traits for them chat completion structs

add reasoning_content under message and delta message in lib/async-openai

Co-authored-by: Graham King <grahamk@nvidia.com>

feat: Add frontend support for `min_tokens` and `ignore_eos` (outside of `nvext`) and Structured Output / Guided Decoding (#2380)
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
Co-authored-by: Ayush Agarwal <ayushag@nvidia.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.

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.

New vllm and sglang engines that run in a sub-process. Will hopefully replace the existing embedded python engines.
    
Why?
    
  - Pure Python, does not require knowing Rust to work on it. Much simpler to maintain.
  - No embedded Python interpreter which avoids linking libpython and avoids the MacOS virtualenv issues.
  - Should have better performance as it's "native" vllm / sglang.
  - Works with any version of vllm (including v1!) and sglang. Less upgrade struggle.

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

Part of https://github.com/ai-dynamo/dynamo/issues/743

Adds support for specifying default request parameters through a json template file that can be applied across all inference requests. This enables consistent parameter settings while still allowing per-request overrides.

Changes:
- Add --request-template CLI flag to specify template file path
- Integrate template support in HTTP, batch and text input modes
- Template values can be overridden by individual request parameters
- Example template.json:
```
{
    "model": "Qwen2.5-3B-Instruct",
    "temperature": 0.7,
    "max_completion_tokens": 4096
}
```

As a first step towards KV routing:
- introduce a `--router-mode` in dynamo-run that only does random and round-robin right now. Not that interesting yet.
- Make the vllm engine publish the KV events received from our patched vllm.

Now we "just" need to connect the two. Easy right?

Under load it sometimes drops a request. The request gets added to the batch (sequence) and immediately gets a FinishReason Stop. Not sure why. It doesn't happen with the default scheduler (non-paged attention), so switch to that for now.

```
dynamo-run in=batch:prompts.jsonl out=mistralrs ~/llm_models/Llama-3.2-3B-Instruct/
```

The file has genai format, one entry per line:
```
{"text": "the prompt"}
{"text": ..etc
```

The prompt is evaluated and the output written to `output.jsonl` in the
same folder as the input.

At the end of the run various statistics are printed:
> Ran 5 files in 8s 679ms. Tokens in: 40 (5/s). Tokens out: 346 (43/s)

This is also helpful for pushing load into the system and stressing the
various components. Not intended for performance measurement, it's a
batch inference tool.