Qwen2.5-VL-32B-Instruct-FlagOS-Nvidia

Introduction

Qwen2.5-VL-32B-Instruct-FlagOS-Nvidia provides an all-in-one deployment solution, enabling execution of Qwen2.5-VL-32B-Instruct on Nvidia GPUs. As the first-generation release for the NVIDIA-H100, this package delivers three key features:

1. Comprehensive Integration:
   • Integrated with FlagScale (https://github.com/FlagOpen/FlagScale).
   • Open-source inference execution code, preconfigured with all necessary software and hardware settings.
   • Pre-built Docker image for rapid deployment on NVIDIA-H100.
2. Consistency Validation:
   • Evaluation tests verifying consistency of results between the official and ours.

Technical Summary

Serving Engine

We use FlagScale as the serving engine to improve the portability of distributed inference.

FlagScale is an end-to-end framework for large models across multiple chips, maximizing computational resource efficiency while ensuring model effectiveness. It ensures both ease of use and high performance for users when deploying models across different chip architectures:

• One-Click Service Deployment: FlagScale provides a unified and simple command execution mechanism, allowing users to fast deploy services seamlessly across various hardware platforms using the same command. This significantly reduces the entry barrier and enhances user experience.
• Automated Deployment Optimization: FlagScale automatically optimizes distributed parallel strategies based on the computational capabilities of different AI chips, ensuring optimal resource allocation and efficient utilization, thereby improving overall deployment performance.
• Automatic Operator Library Switching: Leveraging FlagScale's unified Runner mechanism and deep integration with FlagGems, users can seamlessly switch to the FlagGems operator library for inference by simply adding environment variables in the configuration file.

Triton Support

We validate the execution of Qwen2.5-VL-32B-Instruct model with a Triton-based operator library as a PyTorch alternative.

We use a variety of Triton-implemented operation kernels—approximately 70%—to run the Qwen2.5-VL-32B-Instruct model. These kernels come from two main sources:

• Most Triton kernels are provided by FlagGems (https://github.com/FlagOpen/FlagGems). You can enable FlagGems kernels by setting the environment variable USE_FLAGGEMS. For more details, please refer to the "How to Run Locally" section.

• Also included are Triton kernels from vLLM, including fused MoE.

Bundle Download

Evaluation Results

Benchmark Result

How to Run Locally

📌 Getting Started

Download open-source weights

pip install modelscope
modelscope download --model Qwen/Qwen2.5-VL-32B-Instruct --local_dir <Cache Path>

Download the FlagOS image

docker pull nvcr.io/nvidia/pytorch:24.09-py3

Start the inference service

docker run --rm --init --detach \
  --net=host --uts=host --ipc=host \
  --security-opt=seccomp=unconfined \
  --privileged=true \
  --ulimit stack=67108864 \
  --ulimit memlock=-1 \
  --ulimit nofile=1048576:1048576 \
  --shm-size=32G \
  -v /share:/share \
  --gpus all \
  --name flagos \
  nvcr.io/nvidia/pytorch:24.09-py3 \
  sleep infinity

docker exec -it flagos bash

Serve

flagscale serve qwenvl32-nv-flagos

Contributing

We warmly welcome global developers to join us:

1. Submit Issues to report problems
2. Create Pull Requests to contribute code
3. Improve technical documentation
4. Expand hardware adaptation support

📞 Contact Us

Scan the QR code below to add our WeChat group send "FlagRelease"

License

This project and related model weights are licensed under the MIT License.