---
license: cc-by-nc-sa-4.0
base_model: InternRobotics/InternVLA-N1-DualVLN
tags:
  - vision-language-action
  - navigation
  - quantized
  - tensorrt
  - fp8
pipeline_tag: robotics
---

# InternVLA-N1-DualVLN — FP8

FP8 quantization of [InternRobotics/InternVLA-N1-DualVLN](https://huggingface.co/InternRobotics/InternVLA-N1-DualVLN),
for deployment on NVIDIA Jetson Thor with [TensorRT Edge-LLM](https://github.com/NVIDIA/TensorRT-Edge-LLM). This support is pending review as [NVIDIA/TensorRT-Edge-LLM#193](https://github.com/NVIDIA/TensorRT-Edge-LLM/pull/193); until it merges, build from that PR's branch directly from the upstream repo:

```bash
git clone https://github.com/NVIDIA/TensorRT-Edge-LLM.git
cd TensorRT-Edge-LLM
git fetch origin pull/193/head:internvla-n1
git checkout internvla-n1
```

## What's quantized

InternVLA-N1-DualVLN is a dual-system vision-language navigation model: a Qwen2.5-VL-7B planner
(System 2) plus a flow-matching trajectory expert with a DINOv2 memory block (System 1), joined
by a `z_latents` bridge. **Only System 2 is quantized here.** System 1 and the bridge
(`cond_projector`, `latent_queries`) are kept at the source dtype — the bridge is four rows
through a Linear/GELU/Linear, so quantizing it saves nothing measurable and would put error
directly on the tensor System 1 steers by.

Produced with `tensorrt-edgellm-quantize llm --quantization fp8`, verified end to end:
`model_type` reads `internvla_n1`, and `cond_projector` / `latent_queries` / `traj_dit` /
`rgb_model` are present and unquantized in the export.

## Measured on Jetson Thor (sm_110, JetPack 7.1, TensorRT 10.13.3.9)

| | prefill (1024 tok) | decode (pastKV 1024) | first plan | control rate | engine |
|---|---|---|---|---|---|
| PyTorch bf16 | 328.9 ms | 99.4 ms | 160 ms | 208.1 ms (4.8 Hz) | ~15 GB |
| **This checkpoint** | **90.6 ms** | **32.8 ms** | **118 ms** | **61.3 ms (16.3 Hz)** | **7.10 GB** |

**Closed-loop navigation success**, 199 R2R val_unseen episodes (habitat-sim on Thor,
`VLN_TRAJ_SEED=100`), against PyTorch bf16 (69.8% SR):

| SR | agrees with PyTorch | McNemar p |
|---|---|---|
| 68.3% | 166/199 | 0.728 |

Not distinguishable from PyTorch at this sample size (p = 0.728). See the
[PR that added this support](https://github.com/NVIDIA/TensorRT-Edge-LLM/pull/193) for the
full validation, including why offline metrics like bridge/trajectory cosine were tried and
rejected as acceptance criteria for this model — closed-loop SR is the only thing that agreed
with itself across quantization schemes.

## Usage

Export and build with TensorRT Edge-LLM:

```bash
tensorrt-edgellm-export /path/to/this/checkpoint ./onnx
export EDGELLM_PLUGIN_PATH=.../libNvInfer_edgellm_plugin.so

build/examples/llm/llm_build --onnxDir onnx/llm --engineDir engines/llm \
    --maxBatchSize 1 --maxInputLen 3072 --maxKVCacheCapacity 4096
```

System 1 is not part of this checkpoint's quantization and is built separately — see the
model's runtime guide, `experimental_models/internvla_n1/README.md` in the checked-out branch above (or on [PR #193](https://github.com/NVIDIA/TensorRT-Edge-LLM/pull/193) once merged)
for the full export → build → run flow (both systems, asynchronous, one process).

## License

Inherits the source model's license, CC BY-NC-SA 4.0. Non-commercial use, share-alike,
attribution required. See [InternRobotics/InternVLA-N1-DualVLN](https://huggingface.co/InternRobotics/InternVLA-N1-DualVLN)
for the full terms.

## Citation

If you use this checkpoint, please cite the original model:

```bibtex
@misc{internvla-n1,
    title = {{InternVLA-N1: An} Open Dual-System Navigation Foundation Model with Learned Latent Plans},
    author = {InternVLA-N1 Team},
    year = {2025},
    booktitle={arXiv},
}
@misc{wei2025groundslowfastdualsystem,
      title={Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation},
      author={Meng Wei and Chenyang Wan and Jiaqi Peng and Xiqian Yu and Yuqiang Yang and Delin Feng and Wenzhe Cai and Chenming Zhu and Tai Wang and Jiangmiao Pang and Xihui Liu},
      year={2025},
      eprint={2512.08186},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2512.08186},
}
```