{
"Version" : "1.0.0",
"ServerConfig" :
{
"ipAddress" : "127.0.0.1",
"managementIpAddress" : "127.0.0.2",
"port" : 1025,
"managementPort" : 1026,
"metricsPort" : 1027,
"allowAllZeroIpListening" : false,
"maxLinkNum" : 1000,
"httpsEnabled" : true,
"fullTextEnabled" : false,
"tlsCaPath" : "security/ca/",
"tlsCaFile" : ["ca.pem"],
"tlsCert" : "security/certs/server.pem",
"tlsPk" : "security/keys/server.key.pem",
"tlsCrlPath" : "security/certs/",
"tlsCrlFiles" : ["server_crl.pem"],
"managementTlsCaFile" : ["management_ca.pem"],
"managementTlsCert" : "security/certs/management/server.pem",
"managementTlsPk" : "security/keys/management/server.key.pem",
"managementTlsCrlPath" : "security/management/certs/",
"managementTlsCrlFiles" : ["server_crl.pem"],
"metricsTlsCaFile" : ["metrics_ca.pem"],
"metricsTlsCert" : "security/certs/metrics/server.pem",
"metricsTlsPk" : "security/keys/metrics/server.key.pem",
"metricsTlsCrlPath" : "security/metrics/certs/",
"metricsTlsCrlFiles" : ["server_crl.pem"],
"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",
"interCommTlsCrlPath" : "security/grpc/certs/",
"interCommTlsCrlFiles" : ["server_crl.pem"],
"openAiSupport" : "vllm",
"tokenTimeout" : 600,
"e2eTimeout" : 600,
"distDPServerEnabled":false,
"layerwiseDisaggregated" : false,
"layerwiseDisaggregatedRoleType" : "",
"layerwiseDisaggregatedMasterIpAddress" : "127.0.0.3",
"layerwiseDisaggregatedSlaveIpAddress" : ["127.0.0.4"],
"layerwiseDisaggregatedDataPort" : 10024,
"layerwiseDisaggregatedCrtlPort" : [10001,10002],
"HealthCheckConfig" :
{
"npuUsageThreshold" : 0
}
},
"BackendConfig" : {
"backendName" : "mindieservice_llm_engine",
"modelInstanceNumber" : 1,
"npuDeviceIds" : [[0,1,2,3]],
"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",
"interNodeTlsCrlPath" : "security/grpc/certs/",
"interNodeTlsCrlFiles" : ["server_crl.pem"],
"kvPoolConfig" : {"backend":"", "configPath":""},
"ModelDeployConfig" :
{
"maxSeqLen" : 2560,
"maxInputTokenLen" : 2048,
"truncation" : 0,
"ModelConfig" : [
{
"modelInstanceType" : "Standard",
"modelName" : "llama_65b",
"modelWeightPath" : "/data/atb_testdata/weights/llama1-65b-safetensors",
"worldSize" : 4,
"cpuMemSize" : 0,
"npuMemSize" : -1,
"backendType" : "atb",
"trustRemoteCode" : false,
"async_scheduler_wait_time": 120,
"kv_trans_timeout": 10,
"kv_link_timeout": 1080,
"models" : {
"layerwiseDisaggregatedMasterDeviceNum" : 2,
"layerwiseDisaggregatedSlaveDeviceNum" : 8
}
}
]
},
"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,
"maxFirstTokenWaitTime": 2500
}
},
"LogConfig": {
"dynamicLogLevel" : "",
"dynamicLogLevelValidHours" : 2,
"dynamicLogLevelValidTime" : ""
},
"EnableDynamicAdjustTimeoutConfig": false
}