GitLab

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.

Previously any error would cause us to halt. Most of them are recoverable. So now we print the error and return to the prompt.

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.

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
}
```

"echo_core" is an engine that echoes the post-processed request back to you so you can see the template. Good for testing. It needed an extra flag set to work correctly.

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?

Previously several parts of the stack ensured max tokens (for this single request) was set.

Now only text input sets it (to 8k). Everything else leaves as is, potentially blank. The engines themselves have very small defaults, 16 for vllm and 128 for sglang.

Also fix dynamo-run CUDA startup message to only print if we're using an engine that would benefit from it (mistralrs, llamacpp).

```
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.

Previously we tokenized and counted tokens to stop when max tokens was reached. Now we let the mistral.rs engine do it which saves the extra tokenization step.

Also dynamo-run prints which engines are compiled in in help message, and some minor lint fixes.

- Any engine can take the name of a Hugging Face repository. It will be downloaded before calling the engine.

- The default engine (previously always mistralrs) depends on what is compiled in.

- Text can be piped in and will result in a single run of the model.

All of those together mean if you build with `--features vllm` you can do this and it will download the model and run it with vllm, answer your question, and exit:
```
echo "What is the capital of Costa Rica?"  | dynamo-run Qwen/Qwen2.5-3B-Instruct
```
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

If the python file raises an exception we print it like Python would.

```
$ ./target/debug/dynamo-run in=http out=pystr:~/Temp/cn47/1_e.py --model-name test

Traceback (most recent call last):
  File "/home/graham/Temp/cn47/1_e.py", line 17, in generate
    raise MyException("The message")
1_e.MyException: The message
```

Co-authored-by: Biswa Panda <biswa.panda@gmail.com>

There are two etcd keys:
- The service
- The model

The second one is the interesting one for us. Previously we confused the two.

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

Needs more testing but good enough for now. I get the same results with this as with `vllm serve`.

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

Add backend type `EngineConfig::StaticCore` that wraps the engine in a preprocessor (prompt templating and tokenization).

Add example engine `echo_core` (`out=echo_core`) which takes and returns tokens. A nice side effect is that it echos the full prompt template with system prompt, whereas `echo_full` echos only user prompt.

![image](https://github.com/user-attachments/assets/27ec0a7b-a27d-4e69-96ea-1ffa0822ea90)

Signed-off-by: Ryan McCormick <rmccormick@nvidia.com>

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

Add support in tio for distributed components and discovery.

Node 1:
```
tio in=http out=tdr://ns/backend/mistralrs
```

Node 2:
```
tio in=tdr://ns/backend/mistralrs out=mistralrs ~/llm_models/Llama-3.2-3B-Instruct
```

This will use etcd to auto-discover the model and NATS to talk to it. You can run multiple workers on the same endpoint and it will pick one at random each time.

The `ns/backend/mistralrs` are purely symbolic, pick anything as long as it has three parts, and it matches the other node.

Signed-off-by: Ryan Olson <ryanolson@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

This provides a simple example of how to write a triton-llm engine, and how to connect it to the OpenAI HTTP server.

This is the tool previously called `nio` and `llmctl`.

- **Inputs**: Text and HTTP.
- **Engines**: Echo, which streams your prompt back with a slight delay.

Build: `cargo build`

Pre-requisites: `nats-server` and `etcd` must be running locally, even though they are not yet used by `tio`.

Run with text input:
```
./target/debug/tio in=text out=echo_full --model-name test
```

Run with the triton-llm HTTP server:
```
./target/debug/tio in=http out=echo_full --http-port 8080 --model-name Echo-0B
```

List models:
```
curl localhost:8080/v1/models | jq
```

Will output
```
{
  "object": "list",
  "data": [
    {
      "id": "Echo-0B",
      "object": "object",
      "created": 1739400430,
      "owned_by": "nvidia"
    }
  ]
}
```

#### What's next

As triton-distributed gains features `tio` will be able to grow:
- When we get the pre-processor we can have token-in token-out engines. 
- When we get a pull-router we can have `in=nats` and `out=nats`.
- When we get discovery we can have dynamic engines.