/usr/local/Ascend/mindie/latest/mindie-service/conf/config.json:
{
"OtherParam" :
{
"ResourceParam" :
{
"cacheBlockSize" : 128
},
"LogParam" :
{
"logLevel" : "Info",
"logPath" : "logs/mindservice.log"
},
"ServeParam" :
{
"ipAddress" : "127.0.0.1",
"managementIpAddress" : "127.0.0.2",
"port" : 1025,
"managementPort" : 1026,
"maxLinkNum" : 1000,
"httpsEnabled" : true,
"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" : 4096,
"npuDeviceIds" : [[0,1,2,3]],
"multiNodesInferEnabled" : false,
"ModelParam" : [
{
"modelInstanceType" : "Standard",
"modelName" : "llama_65b",
"modelWeightPath" : "/usr/local/LLM_models/Qwen1___5-14B-Chat",
"worldSize" : 4,
"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
}
}
{
"OtherParam" :
{
"ResourceParam" :
{
"cacheBlockSize" : 128
},
"LogParam" :
{
"logLevel" : "Info",
"logPath" : "logs/mindservice.log"
},
"ServeParam" :
{
"ipAddress" : "127.0.0.1",
"managementIpAddress" : "127.0.0.2",
"port" : 1025,
"managementPort" : 1026,
"maxLinkNum" : 1000,
"httpsEnabled" : true,
"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" : 4096,
"npuDeviceIds" : [[0,1,2,3]],
"multiNodesInferEnabled" : false,
"ModelParam" : [
{
"modelInstanceType" : "Standard",
"modelName" : "llama_65b",
"modelWeightPath" : "/usr/local/LLM_models/Qwen1___5-14B-Chat",
"worldSize" : 4,
"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
}
}
/usr/local/Ascend/mindie/latest/mindie-service路径下运行./bin/mindservice_daemon时报错:

检查config.json文件中"modelWeightPath"是没问题的。