GitLab

- Add Granite to our tokenizer
- Fix pre-processor to load context length correctly
- Add strftime_now Jinja function for prompt templates
- Update llama.cpp
- Handle trtllm errors when not using trtllm

Support depends on the engine:

- `mistral.rs`, our default engine, doesn't support Granite yet.

- `llama.cpp` does and works very well:
```
dynamo-run out=llamacpp ~/llms/granite-3.3-2b-instruct-Q4_K_M.gguf --context-length 16384
```

- `vllm` also works very well:
```
dynamo-run in=http out=vllm ~/llms/granite-3.3-2b-instruct --context-length 16384
```

- `sglang` mostly works, but it doesn't catch the stop token, so we do in the HTTP ingress, and log an error. The Text ingress doesn't catch it because I disabled it to make the raw echo engine work. A bit of work to do here.

Closes: #1245 

It was removed from the docs in 0.2.1 and replaced with writing a [standalone Python engine](https://github.com/ai-dynamo/dynamo/blob/main/docs/guides/dynamo_run.md#writing-your-own-engine-in-python).

Also remove the associated `dynamo-run` feature `python`.

Releasing this in 0.3.0 will resolve #784 and #1109.

Example:
```
dynamo-run out=<engine> <model> --kv-cache-block-size 64
```

In a distributed system this goes on the worker node and is propagated to ingress via the model deployment card.

Previously hard coded to 16, which is now the default.

- Load context_length from model. Closes #1172
- Store context length and KV cache block size in Model Deployment Card #1170

Co-authored-by: Suman Tatiraju <statiraju@statiraju-mlt.client.nvidia.com>

Signed-off-by: Suman Tatiraju <167138127+statiraju@users.noreply.github.com>
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Co-authored-by: Kristen Kelleher <kkelleher@nvidia.com>
Co-authored-by: Suman Tatiraju <statiraju@statiraju-mlt.client.nvidia.com>
Co-authored-by: Hannah Zhang <hannahz@nvidia.com>

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

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.

Example of how to connect a Python sglang engine to the message bus (NATS/etc). I

In this example sglang does the pre/post processing. There is already an example where Dynamo does it.

The examples teach this:

- Be a chat completions engine, do your own pre-processing:

```
await register_llm(ModelType.Chat, endpoint, config.model)
```

- Have Dynamo do pre-processing. It will register us under both Chat and Completions endpoints, because that's handled before a Backend engine gets the request:

```
await register_llm(ModelType.Backend, endpoint, config.model)
```

Allow both password or TLS auth, if none of these is provided fallback to no auth

Closes #657

Co-authored-by: ishandhanani <ishandhananai@gmail.com>

. New mistralrs and llamacpp version
. mistralrs: Handle Gemma 3 and Llama 4 as vision models
. Update the dynamo-run docs to use Qwen 3
. Our pre-processor now supports Llama 4's newer multi-modal `config.json`
. Upgrade minijinja to handle Qwen 3's prompt template

For Llama 4 we'll need to limit the max seq len. vllm says:
> To serve at least one request with the models's max seq len (10485760), (240.00 GiB KV cache is needed,...

I was able to run Llama 4 with llamacpp and a quantized GGUF, with Dynamo doing the pre-processing.

Signed-off-by: Graham King <graham@gkgk.org>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

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

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

Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Co-authored-by: ishandhanani <ishandhanani@gmail.com>
Co-authored-by: Ubuntu <ubuntu@dev-inst-2w1vokvyuts83rzn4n1k7mnzew9.us-central1-a.c.brevdevprod.internal>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>

Signed-off-by: Harrison Saturley-Hall <454891+saturley-hall@users.noreply.github.com>