华为昆仑2280鲲鹏920昇腾ATLAS300IPro虚拟化FusionCompute离线搭建MindIe环境调用DeepSeek-R1-14B

leilei309

1217人浏览 · 2025-08-13 16:23:26

leilei309 · 2025-08-13 16:23:26 发布

花费3周时间，从硬件驱动和固件安装以及虚拟化直通GPU资源，再到虚拟化安装Docker，Docker加载离线MindIe,再去传参调用Deepseek蒸馏模型，并返回相应的值。

一、环境准备

1.宿主机：openEuler20

2.虚拟化：FusionCompute 8.5.0.SPC200

3.虚拟服务器：麒麟V10Sp3

备注：目前ATLAS300IPRO只支持麒麟V10Sp2、麒麟V10Sp3、Centos7.6

二、软件下载

1.ATLAS300IPro驱动及固件

2.Mindie离线系统

3.模型文件

三、固件环境参数调整

1.宿主机登录BIOS，修改BIOS中SSMU配置为Enable

四、虚拟服务器直通GPU

1.首先在虚拟化软件中建立GPU资源组，将GPU物理卡纳入资源组中；

2.将虚拟机关机之后，通过配置中的硬件，将GPU资源组与对应的虚拟机进行绑定。

五、安装DOcker

1.下载docker离线安装包；

2.解压覆盖并执行docker安装；

tar -zxvf  docker-24.0.9
cp -r docker/* /usr/bin/
vi /usr/lib/systemd/system/docker.service
[Unit]
Description=Docker Application Container Engine
Documentation=https://docs.docker.com
After=network-online.target firewalld.service
Wants=network-online.target
[Service]
Type=notify
ExecStart=/usr/bin/dockerd
ExecReload=/bin/kill -s HUP $MAINPID
LimitNOFILE=infinity
LimitNPROC=infinity
TimeoutStartSec=0
Delegate=yes
KillMode=process
Restart=on-failure
StartLimitBurst=3
StartLimitInterval=60s
[Install]
WantedBy=multi-user.target
chmod +x /usr/lib/systemd/system/docker.service
vi /etc/docker/daemon.json
{
"registry-mirrors": ["https://registry.docker-cn.com"],
"exec-opts": ["native.cgroupdriver=systemd"]
}
systemctl daemon-reload
systemctl start docker
systemctl enable docker

六、Docker加载mindie

docker ps -a   查看镜像
docker load -i mindie_1.0.0-300I-Duo-py311-openeuler24.03-lts  载入镜像
docker run -it -d --net=host --shm-size=1g \
    --name mindie_container \
    --device=/dev/davinci_manager \
    --device=/dev/hisi_hdc \
    --device=/dev/devmm_svm \
    --device=/dev/davinci0 \
    --device=/dev/davinci2 \
    -v /usr/local/Ascend/driver:/usr/local/Ascend/driver:ro \
    -v /usr/local/sbin:/usr/local/sbin:ro \
    -v /home/DeepSeek-R1-Distill-Qwen-14B:/model:rw \
    swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:1.0.0-300I-Duo-py311-openeuler24.03-lts bash  运行镜像
docker exec -it mindie_container bash  进入镜像
docker rm -f mindie_container_new 删除镜像

七、调用大模型修改配置文件Confin.json文件

docker exec -it mindie_container bash


sed -i 's/"torch_dtype": "bfloat16"/"torch_dtype": "float16"/' config.json

vi /usr/local/Ascend/mindie/latest/mindie-service/conf/config.json

{
    "Version" : "1.1.0",
    "LogConfig" :
    {
        "logLevel" : "Info",
        "logFileSize" : 20,
        "logFileNum" : 20,
        "logPath" : "logs/mindservice.log"
    },

    "ServerConfig" :
    {
        "ipAddress" : "192.168.0.248",
        "managementIpAddress" : "127.0.0.2",
        "port" : 1025,
        "managementPort" : 1026,
        "metricsPort" : 1027,
        "allowAllZeroIpListening" : false,
        "maxLinkNum" : 1000,
        "httpsEnabled" : false,
        "fullTextEnabled" : false,
        "tlsCaPath" : "security/ca/",
        "tlsCaFile" : ["ca.pem"],
        "tlsCert" : "security/certs/server.pem",
        "tlsPk" : "security/keys/server.key.pem",
        "tlsPkPwd" : "security/pass/key_pwd.txt",
        "tlsCrlPath" : "security/certs/",
        "tlsCrlFiles" : ["server_crl.pem"],
        "managementTlsCaFile" : ["management_ca.pem"],
        "managementTlsCert" : "security/certs/management/server.pem",
        "managementTlsPk" : "security/keys/management/server.key.pem",
        "managementTlsPkPwd" : "security/pass/management/key_pwd.txt",
        "managementTlsCrlPath" : "security/management/certs/",
        "managementTlsCrlFiles" : ["server_crl.pem"],
        "kmcKsfMaster" : "tools/pmt/master/ksfa",
        "kmcKsfStandby" : "tools/pmt/standby/ksfb",
        "inferMode" : "standard",
        "interCommTLSEnabled" : true,
        "interCommPort" : 1121,
        "interCommTlsCaPath" : "security/grpc/ca/",
        "interCommTlsCaFiles" : ["ca.pem"],
        "interCommTlsCert" : "security/grpc/certs/server.pem",
        "interCommPk" : "security/grpc/keys/server.key.pem",
        "interCommPkPwd" : "security/grpc/pass/key_pwd.txt",
        "interCommTlsCrlPath" : "security/grpc/certs/",
        "interCommTlsCrlFiles" : ["server_crl.pem"],
        "openAiSupport" : "vllm"
    },

    "BackendConfig" : {
        "backendName" : "mindieservice_llm_engine",
        "modelInstanceNumber" : 1,
        "npuDeviceIds" : [[0,1]],
        "tokenizerProcessNumber" : 8,
        "multiNodesInferEnabled" : false,
        "multiNodesInferPort" : 1120,
        "interNodeTLSEnabled" : true,
        "interNodeTlsCaPath" : "security/grpc/ca/",
        "interNodeTlsCaFiles" : ["ca.pem"],
        "interNodeTlsCert" : "security/grpc/certs/server.pem",
        "interNodeTlsPk" : "security/grpc/keys/server.key.pem",
        "interNodeTlsPkPwd" : "security/grpc/pass/mindie_server_key_pwd.txt",
        "interNodeTlsCrlPath" : "security/grpc/certs/",
        "interNodeTlsCrlFiles" : ["server_crl.pem"],
        "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa",
        "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb",
        "ModelDeployConfig" :
        {
            "maxSeqLen" : 2560,
            "maxInputTokenLen" : 2048,
            "truncation" : false,
            "ModelConfig" : [
                {
                    "modelInstanceType" : "Standard",
                    "modelName" : "DeepSeek-R1-Distill-Qwen-14B",
                    "modelWeightPath" : "/model",
                    "worldSize" : 2,
                    "cpuMemSize" : 5,
                    "npuMemSize" : -1,
                    "backendType" : "atb",
                    "trustRemoteCode" : false
                }
            ]
        },

        "ScheduleConfig" :
        {
            "templateType" : "Standard",
            "templateName" : "Standard_LLM",
            "cacheBlockSize" : 128,

            "maxPrefillBatchSize" : 50,
            "maxPrefillTokens"  : 8192,
            "prefillTimeMsPerReq" : 150,
            "prefillPolicyType" : 0,

            "decodeTimeMsPerReq" : 50,
            "decodePolicyType" : 0,

            "maxBatchSize" : 200,
            "maxIterTimes" : 512,
            "maxPreemptCount" : 0,
            "supportSelectBatch" : false,
            "maxQueueDelayMicroseconds" : 5000
        }
    }
}

八、设置大模型环境变量

source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh
source /usr/local/Ascend/atb-models/set_env.sh
source /usr/local/Ascend/mindie/set_env.sh

九、启动Mindie服务

cd /usr/local/Ascend/mindie/latest/mindie-service/bin
./mindieservice_daemon

十、服务器之间测试验证

curl 192.168.0.248:1025/generate -d '{
  "prompt": "你是谁?",
  "max_tokens": 32,
  "stream": false,
  "do_sample": true,
  "repetition_penalty": 1.00,
  "temperature": 0.01,
  "top_p": 0.001,
  "top_k": 1,
  "model": "DeepSeek-R1-Distill-Qwen-14B"
}'