{
    "Version": "1.0.0",
    "LogConfig": {
        "logLevel": "Info",
        "logFileSize": 20,
        "logFileNum": 20,
        "logPath": "logs/mindservice.log"
    },
    "BackendConfig": {
        "backendName": "mindieservice_llm_engine",
        "modelInstanceNumber": 1,
        "npuDeviceIds": [
            [
                0,
                1,
                2,
                3
            ]
        ],
        "tokenizerProcessNumber": 8,
        "multiNodesInferEnabled": true,
        "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"
        ],
        "ModelDeployConfig": {
            "maxSeqLen": 2560,
            "maxInputTokenLen": 2048,
            "truncation": 0,
            "ModelConfig": [
                {
                    "modelInstanceType": "StandardMock",
                    "modelName": "llama_65b",
                    "modelWeightPath": "/home/data/Meta-Llama-3-8B/",
                    "worldSize": 4,
                    "cpuMemSize": 5,
                    "npuMemSize": -1,
                    "backendType": "ms",
                    "trustRemoteCode": false,
                    "plugin_params": "{\"plugin_type\":\"prefix_cache\"}"
                }
            ],
            "LoraModules": [
                {
                    "name": "test",
                    "path": "test",
                    "baseModelName": "test"
                }
            ]
        },
        "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,
            "enablePrefixCache": true
        }
    }
}