2024-08-26 11:16:11.210212 8960 Log started at [trace] level
2024-08-26 11:16:11.210252 8960 Log default format: yyyy-mm-dd hh:mm:ss.uuuuuu threadid loglevel msg
2024-08-26 11:16:11.210784 8960 trace main.cpp:114] [Connector] process 8960 belong to process group: 8930
2024-08-26 11:16:12.205453 8963 trace slave_IPC_communicator.cpp:291] [=========== Backend rank 0, start processing the broadcast message =============]
2024-08-26 11:16:12.205402 8932 trace master_IPC_communicator.cpp:198] Ready to send init message length: 1211
2024-08-26 11:16:12.205421 8932 trace master_IPC_communicator.cpp:206] Send init message to connector success!.
2024-08-26 11:16:12.365996 8963 trace slave_IPC_communicator.cpp:312] [=========== Backend rank 0 is Single Node Infer =============]
2024-08-26 11:16:22.480833 8963 error LLMModelExecutorPython.cpp:56] LLMPythonModel initializes fail: modelWrapper return status is error
2024-08-26 11:16:22.481266 8963 error slave_IPC_communicator.cpp:317] [SlaveIPCCommunicator::ProcessBroadcastRecvMessage]Executor failed to init model
2024-08-26 11:16:22.481379 8963 error slave_IPC_communicator.cpp:438] [HandleRcvMsg]Executor failed to process recv broadcastMessage
2024-08-26 11:16:22.481392 8963 error slave_IPC_communicator.cpp:446] [HandleRcvMsg]slave communicator notify connector to terminate
2024-08-26 11:16:22.481401 8963 warning main.cpp:24] [Backend connector]Signal 15 received, exiting the process
2024-08-26 11:16:25.262252 8932 warning llm_daemon.cpp:61] [Daemon] received exit signal[17]

{
    "OtherParam" :
    {
        "ResourceParam" :
        {
            "cacheBlockSize" : 128
        },
        "LogParam" :
        {
            "logLevel" : "Verbose",
            "logPath" : "logs/mindservice.log"
        },
        "ServeParam" :
        {
            "ipAddress" : "127.0.0.1",
            "port" : 1025,
            "maxLinkNum" : 1000,
            "httpsEnabled" : false,
            "tlsCaPath" : "security/ca/",
            "tlsCaFile" : ["ca.pem"],
            "tlsCert" : "security/certs/server.pem",
            "tlsPk" : "security/keys/server.key.pem",
            "tlsPkPwd" : "security/pass/mindie_server_key_pwd.txt",
            "tlsCrl" : "security/certs/server_crl.pem",
            "managementTlsCaFile" : ["management_ca.pem"],
            "managementTlsCert" : "security/certs/management_server.pem",
            "managementTlsPk" : "security/keys/management_server.key.pem",
            "managementTlsPkPwd" : "security/pass/management_mindie_server_key_pwd.txt",
            "managementTlsCrl" : "security/certs/management_server_crl.pem",
            "kmcKsfMaster" : "tools/pmt/master/ksfa",
            "kmcKsfStandby" : "tools/pmt/standby/ksfb",
            "multiNodesInferPort" : 1120,
            "interNodeTLSEnabled" : true,
            "interNodeTlsCaFile" : "security/ca/ca.pem",
            "interNodeTlsCert" : "security/certs/server.pem",
            "interNodeTlsPk" : "security/keys/server.key.pem",
            "interNodeTlsPkPwd" : "security/pass/mindie_server_key_pwd.txt",
            "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa",
            "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb"
        }
    },
    "WorkFlowParam" :
    {
        "TemplateParam" :
        {
            "templateType" : "Standard",
            "templateName" : "Standard_llama"
        }
    },
    "ModelDeployParam" :
    {
        "engineName" : "mindieservice_llm_engine",
        "modelInstanceNumber" : 1,
        "tokenizerProcessNumber" : 8,
        "maxSeqLen" : 2560,
        "npuDeviceIds" : [[0]],
        "multiNodesInferEnabled" : false,
        "ModelParam" : [
            {
                "modelInstanceType" : "Standard",
                "modelName" : "deepseek",
                "modelWeightPath" : "/home/deepseek-coder-6.7b-instruct",
                "worldSize" : 1,
                "cpuMemSize" : 5,
                "npuMemSize" : 8,
                "backendType" : "atb",
                "pluginParams" : ""
            }
        ]
    },
    "ScheduleParam" :
    {
        "maxPrefillBatchSize" : 50,
        "maxPrefillTokens" : 8192,
        "prefillTimeMsPerReq" : 150,
        "prefillPolicyType" : 0,

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

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