单个NPU（Qwen3-Embedding-8B）

单个NPU（Qwen3-Embedding-8B）#

Qwen3 Embedding 模型系列是 Qwen 家族最新的专有模型，专为文本嵌入和排序任务设计。在 Qwen3 系列的密集基础模型之上，它提供了多种尺寸（0.6B、4B 和 8B）的文本嵌入与重排序模型。本指南介绍如何使用 vLLM Ascend 运行该模型。请注意，只有 vLLM Ascend 0.9.2rc1 及更高版本才支持该模型。

运行 docker 容器#

以 Qwen3-Embedding-8B 模型为例，首先使用以下命令运行 docker 容器：

# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:v0.9.2rc1
docker run --rm \
--name vllm-ascend \
--device /dev/davinci0 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it $IMAGE bash

设置环境变量：

# Load model from ModelScope to speed up download
export VLLM_USE_MODELSCOPE=True

# Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256

在线推理#

vllm serve Qwen/Qwen3-Embedding-8B --task embed

一旦服务器启动，就可以通过输入提示词来查询模型。

curl http://localhost:8000/v1/embeddings -H "Content-Type: application/json" -d '{
  "model": "Qwen/Qwen3-Embedding-8B",
  "messages": [
    {"role": "user", "content": "Hello"}
  ]
}'

离线推理#

import torch
import vllm
from vllm import LLM

def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'Instruct: {task_description}\nQuery:{query}'


if __name__=="__main__":
    # Each query must come with a one-sentence instruction that describes the task
    task = 'Given a web search query, retrieve relevant passages that answer the query'

    queries = [
        get_detailed_instruct(task, 'What is the capital of China?'),
        get_detailed_instruct(task, 'Explain gravity')
    ]
    # No need to add instruction for retrieval documents
    documents = [
        "The capital of China is Beijing.",
        "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
    ]
    input_texts = queries + documents

    model = LLM(model="Qwen/Qwen3-Embedding-8B",
                task="embed",
                distributed_executor_backend="mp")

    outputs = model.embed(input_texts)
    embeddings = torch.tensor([o.outputs.embedding for o in outputs])
    scores = (embeddings[:2] @ embeddings[2:].T)
    print(scores.tolist())

如果你成功运行此脚本，你可以看到如下所示的信息：

Adding requests: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 282.22it/s]
Processed prompts:   0%|                                                                                                                                    | 0/4 [00:00<?, ?it/s, est. speed input: 0.00 toks/s, output: 0.00 toks/s](VllmWorker rank=0 pid=4074750) ('Warning: torch.save with "_use_new_zipfile_serialization = False" is not recommended for npu tensor, which may bring unexpected errors and hopefully set "_use_new_zipfile_serialization = True"', 'if it is necessary to use this, please convert the npu tensor to cpu tensor for saving')
Processed prompts: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 31.95it/s, est. speed input: 0.00 toks/s, output: 0.00 toks/s]
[[0.7477798461914062, 0.07548339664936066], [0.0886271521449089, 0.6311039924621582]]
目录