多机部署deepseek-w8a8应该如何配置config.json文件
收藏回复举报
多机部署deepseek-w8a8应该如何配置config.json文件
t('forum.solved') 已解决
发表于2026-01-09 14:08:15
0 查看
以下是我在两台服务器中配置的config.json文件,请问是否有问题,两个机器的配置文件内容完全一样

{

    "Version" : "1.0.0",

    "ServerConfig" :

    {

        "ipAddress" : "服务器a",

        "managementIpAddress" : "127.0.0.2",

        "port" : 1035,

        "managementPort" : 1036,

        "metricsPort" : 1037,

        "allowAllZeroIpListening" : false,

        "maxLinkNum" : 150,

        "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" : false,

        "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],[0,1,2,3,4,5,6,7]],

        "tokenizerProcessNumber" : 8,

        "multiNodesInferEnabled" : true,

        "multiNodesInferPort" : 1120,

        "interNodeTLSEnabled" : false,

        "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" : 24576,

            "maxInputTokenLen" : 16384,

            "truncation" : true,

            "ModelConfig" : [

                {

                    "modelInstanceType" : "Standard",

                    "modelName" : "deepseek_v3.1_w8a8",

                    "modelWeightPath" : "/data/disk02/Deepseek-V3.1-w8a8/",

                    "worldSize" : 16,

                    "cpuMemSize" : 5,

                    "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" : 24576,

            "prefillTimeMsPerReq" : 150,

            "prefillPolicyType" : 0,

            "decodeTimeMsPerReq" : 100,

            "decodePolicyType" : 0,

            "maxBatchSize" : 200,

            "maxIterTimes" : 8192,

            "maxPreemptCount" : 0,

            "supportSelectBatch" : false,

            "maxQueueDelayMicroseconds" : 5000

        }

    }

}

我要发帖子