vllm-plugin-FL

vllm-plugin-FL is a plugin for the vLLM inference/serving framework, built on FlagOS’s unified multi-chip backend — including the unified operator library FlagGems and the unified communication library FlagCX. It extends vLLM’s capabilities and performance across diverse hardware environments. Without changing vLLM’s original interfaces or usage patterns, the same command can run model inference/serving on different chips.

Supported Models and Chips

In theory, vllm-plugin-FL can support all models available in vLLM, as long as no unsupported operators are involved. The tables below summarize the current support status of end-to-end verified models and chips, including both fully supported and in-progress (“Merging”) entries.

Supported Models

Supported Chips

Quick Start

Setup

1. Install vllm from the official v0.19.0 (optional if the correct version is installed) or from the fork vllm-FL.

2. Install vllm-plugin-FL

   2.1 Clone the repository:

   git clone https://github.com/flagos-ai/vllm-plugin-FL

   2.2 install

   cd vllm-plugin-FL
   pip install --no-build-isolation .
   # or editble install
   pip install --no-build-isolation -e .

3. Install FlagGems

   3.1 Install Build Dependencies

   pip install -U scikit-build-core==0.11 pybind11 ninja cmake

   3.2 Installation FlagGems

   git clone https://github.com/flagos-ai/FlagGems
   cd FlagGems
   git checkout v5.0.0
   pip install --no-build-isolation .
   # or editble install
   pip install --no-build-isolation -e .

4. (Optional) Install FlagCX

   4.1 Clone the repository:

   git clone https://github.com/flagos-ai/FlagCX.git
   cd FlagCX
   git checkout -b v0.9.0
   git submodule update --init --recursive

   4.2 Build the library with different flags targeting to different platforms:

   make USE_NVIDIA=1

   4.3 Set environment

   export FLAGCX_PATH="$PWD"

   4.4 Installation FlagCX

   cd plugin/torch/
   FLAGCX_ADAPTOR=[xxx] pip install . --no-build-isolation
   # or editable install
   FLAGCX_ADAPTOR=[xxx] pip install -e . --no-build-isolation

   Note: [xxx] should be selected according to the current platform, e.g., nvidia, ascend, etc.

If there are multiple plugins in the current environment, you can specify use vllm-plugin-fl via VLLM_PLUGINS=’fl’.

Additional Steps for Ascend

1. Install FlagTree

   RES="--index-url=https://resource.flagos.net/repository/flagos-pypi-hosted/simple --trusted-host=https://resource.flagos.net"
   python3 -m pip install flagtree==0.4.0+ascend3.2 $RES

2. Set required environment variable

   export TRITON_ALL_BLOCKS_PARALLEL=1

3. Enable eager execution

   Ascend requires eager execution. Add enforce_eager=True to the LLM constructor or pass --enforce-eager on the command line.

Run a Task

Offline Batched Inference

With vLLM and vLLM-fl installed, you can start generating texts for list of input prompts (i.e. offline batch inferencing). See the example script: offline_inference. Or use blow python script directly.

from vllm import LLM, SamplingParams
import torch
from vllm.config.compilation import CompilationConfig


if __name__ == '__main__':
    prompts = [
        "Hello, my name is",
    ]
    # Create a sampling params object.
    sampling_params = SamplingParams(max_tokens=10, temperature=0.0)
    # Create an LLM.
    llm = LLM(model="Qwen/Qwen3-4B", max_num_batched_tokens=16384, max_num_seqs=2048)
    # Generate texts from the prompts.
    outputs = llm.generate(prompts, sampling_params)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Advanced use

For dispatch environment variable usage, see environment variables usage.

Using Cuda Communication library

If you want to use the original Cuda Communication, you can unset the following environment variables.

unset FLAGCX_PATH

Using native CUDA operators

If you want to use the original CUDA operators, you can set the following environment variables.

export USE_FLAGGEMS=0