惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
A
About on SuperTechFans
Y
Y Combinator Blog
V
V2EX
Engineering at Meta
Engineering at Meta
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
V
Visual Studio Blog
博客园 - 叶小钗
博客园 - 聂微东
阮一峰的网络日志
阮一峰的网络日志
H
Help Net Security
小众软件
小众软件
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
The GitHub Blog
The GitHub Blog
WordPress大学
WordPress大学
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
MongoDB | Blog
MongoDB | Blog
B
Blog
G
Google Developers Blog
J
Java Code Geeks
博客园 - 三生石上(FineUI控件)
IT之家
IT之家
N
Netflix TechBlog - Medium
腾讯CDC

博客园 - badwood

iptables规则笔记 secueCRT脚本再试牛刀 主机基线脚本 大模型部署手册-英伟达 ssl自签证书+nginx 备忘 Claude Code私有化使用 mindie推理框架及工程化 minio-2.使用 minio-1.搭建 旧源消失的rpm包安装-devtoolset-9 vllm-ascend 2/2 -双机推理 MCP-1.hello world vllm-ascend 1/2 -单机推理 ESP32-S3玩具1-使用Arduino evalscope使用2-使用自定义数据集压测 设置fdfs自动启动 FunASR mindie开启DeepSeek的128K xinference推理embedding等小模型 离线安装docker 昇腾910b服务器初始化 evalscope使用1-基础压测 大模型围栏-nginx+lua 大模型私有化部署-deepseek671-mindie dify-2:问题分类器调整
大模型部署手册-昇腾服务器
badwood · 2026-07-31 · via 博客园 - badwood
# config.json文件
{
    "Version" : "1.0.0",

    "ServerConfig" :
    {
        "ipAddress" : "0.0.0.0",
        "managementIpAddress" : "0.0.0.0",
        "port" : 1025,
        "managementPort" : 1026,
        "metricsPort" : 1027,
        "allowAllZeroIpListening" : true,
        "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",
        "tokenTimeout" : 600,
        "e2eTimeout" : 600,
        "distDPServerEnabled":false
    },

    "BackendConfig" : {
        "backendName" : "mindieservice_llm_engine",
        "modelInstanceNumber" : 1,
        "npuDeviceIds" : [[0,1,2,3,4,5,6,7]],
        "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",
        "kvPoolConfig" : {"backend":"", "configPath":""},
        "ModelDeployConfig" :
        {
            "maxSeqLen" : 6400,
            "maxInputTokenLen" : 6000,
            "truncation" : true,
            "ModelConfig" : [
                {
                    "modelInstanceType" : "Standard",
                    "modelName" : "im-30b",
                    "modelWeightPath" : "/models/Qwen3-30B-A3B-Instruct-2507",
                    "worldSize" : 8,
                    "cpuMemSize" : 0,
                    "npuMemSize" : -1,
                    "backendType" : "atb",
                    "trustRemoteCode" : false,
                    "async_scheduler_wait_time": 120,
                    "kv_trans_timeout": 10,
                    "kv_link_timeout": 1080
                }
            ]
        },

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

            "maxPrefillBatchSize" : 50,
            "maxPrefillTokens" : 6000,
            "prefillTimeMsPerReq" : 150,
            "prefillPolicyType" : 0,

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

            "maxBatchSize" : 100,
            "maxIterTimes" : 400,
            "maxPreemptCount" : 0,
            "supportSelectBatch" : false,
            "maxQueueDelayMicroseconds" : 5000,
            "maxFirstTokenWaitTime": 2500
        }
    },

    "LogConfig": {
        "dynamicLogLevel" : "",
        "dynamicLogLevelValidHours" : 2,
        "dynamicLogLevelValidTime" : ""
    }
}
# start.sh
#!/bin/bash
set -euo pipefail
export LD_LIBRARY_PATH=/usr/local/lib64/python3.11/site-packages/torch/lib/:$LD_LIBRARY_PATH
export MIES_SERVICE_MONITOR_MODE=1
cd $MIES_INSTALL_PATH || exit 1

echo "[$(date)] 停止旧的mindieservice_daemon进程..."
pkill -9 -f mindie || true
sleep 5

echo "[$(date)] 启动mindieservice_daemon..."
nohup ./bin/mindieservice_daemon > output.log 2>&1

# 监控服务进程,进程退出则脚本退出(核心:让脚本随服务进程存活)
echo "[$(date)] 监控mindieservice_daemon进程..."
while pgrep -f mindieservice_daemon > /dev/null; do
    sleep 1
done
echo "[$(date)] mindieservice_daemon进程退出,脚本退出"
exit 1