GitLab

Co-authored-by: Graham King <grahamk@nvidia.com>
Co-authored-by: hongkuan <hongkuanz@nvidia.com>
Co-authored-by: Ubuntu <ubuntu@crusoe-prod--inst-2wjuoekvfq72mlpdrcugujrtgfp.us-east1-a.compute.internal>

That avoids passing the `--model-config` param to dynamo-run when using llamacpp.

. 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>

Signed-off-by: Chasing1020 <chasing1020@gmail.com>

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).

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.

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>

Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

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>

Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

"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.

It's different enough that I made a new engine vllm0_8 and renamed the previous engine to vllm0_7.

`dynamo-run out=vllm` now expects 0.8. This matches the container change in #690.

For older use `dynamo-run out=vllm0_7`.

Signed-off-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

Signed-off-by: Maksim Khadkevich <mkhadkevich@nvidia.com>

Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Signed-off-by: Tanmay Verma <tanmayv@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
Signed-off-by: Chantal D Gama Rose <cdgamarose@nvidia.com>
Signed-off-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
Co-authored-by: Julien Mancuso <jmancuso@nvidia.com>
Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
Co-authored-by: mabdulwahhab <mabdulwahhab@nvidia.com>
Co-authored-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
Co-authored-by: cdgamarose-nv <cdgamarose@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com>
Co-authored-by: Suman Tatiraju <167138127+statiraju@users.noreply.github.com>
Co-authored-by: Piotr Marcinkiewicz <piotrm@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>

feat: Extract Common Configs + Log Configs on Init + Add `test_` to `sdk/tests` filenames required for pytest (#434)
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>

#### Overview:

Updated the dynamo run doc `docs/guides/dynamo_run.md`

#### Details:

- Updated the instructions to make it clear which binary to use for built backends
- Reformatted the doc to make it more readable
- Added missing cmake library for ubuntu
Signed-off-by: Chantal D Gama Rose <cdgamarose@nvidia.com>

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

Put the arguments in a JSON file:
```
{
    "dtype": "half",
    "trust_remote_code": true
}
```

Pass it like this:
```
dynamo-run out=sglang ~/llm_models/Llama-3.2-3B-Instruct --extra-engine-args sglang_extra.json
```

Requested here https://github.com/ai-dynamo/dynamo/issues/290 (`dtype`) and here https://github.com/ai-dynamo/dynamo/issues/360 (`trust_remote_code`).

This lets us do:
```
dynamo-run out=llamacpp <gguf_file>
```

Previously a `--model-config <hf-repo>` was also required, to configure our tokenizer.

Co-authored-by: Olga Andreeva <oandreeva@oandreeva-mlt.client.nvidia.com>

Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>