硬件：300I pro

模型：DeepSeek-R1-Distill-7B

运行 ./mindieservice_daemon 的时候报错：

LLMInferEngine failed to init LLMInferModels 

ERR: Failed to init endpoint! Please check the service log or console output. 

Killed

mindservice.log如下：

[2025-04-06 15:49:29.887304+08:00] [419] [421] [server] [ERROR] [llm_infer_model_instance.cpp:234] : [LLMInferModelInstance::Init] llmManager_ init fail! 

[2025-04-06 15:49:29.887347+08:00] [419] [421] [server] [ERROR] [llm_infer_model.cpp:28] : ModelInstance init failed 

[2025-04-06 15:49:29.887383+08:00] [419] [421] [server] [ERROR] [llm_infer_engine.cpp:48] : [MIE05E040001] [llm_backend] LLMInferEngine initialize LLMInfe 

rModels failed. please check the error stacks for more details 

[2025-04-06 15:49:29.887440+08:00] [419] [421] [server] [ERROR] [infer_backend_manager.cpp:272] : [MIE04E060108] [backend_manager] Failed to init engine:  

mindieservice_llm_engine 

[2025-04-06 15:49:29.887465+08:00] [419] [421] [server] [ERROR] [EndPoint endpoint.cpp:50] ERR: Failed to init backendManager! Please check in the mindser 

vice.log, pythonlog.log(default path: mindie-llm/logs) or console output.

/usr/local/Ascend/mindie/latest/mindie-llm/logs如下：

 2025-04-06 15:49:26.092261 421 LLM log default format: [yyyy-mm-dd hh:mm:ss.uuuuuu][processid] [threadid] [llm] [loglevel][file:line] [error code] msg 

[2025-04-06 15:49:26.092286] [419] [139710713542336] [llm] [INFO] [llm_manager_impl.cpp:68] LLMRuntime init success! 

[2025-04-06 15:49:26.093364] [419] [139710713542336] [llm] [INFO] [model_deploy_config.cpp:137] ModelDeployConfig::pySonamelibpython3.11.so 

[2025-04-06 15:49:29.887201] [419] [139710713542336] [llm] [ERROR] [model_deploy_config.cpp:159] Failed to get vocab size from tokenizer wrapper with exception: KeyError: 'model_type' 

 At: 

  /usr/local/Ascend/atb-models/atb_llm/models/__init__.py(30): get_model 

  /usr/local/Ascend/atb-models/atb_llm/runner/tokenizer_wrapper.py(18): __init__ 

  /usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_tokenizer_wrapper.py(8): __init__ 

  /usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/__init__.py(28): get_tokenizer_wrapper 

 

 

/usr/local/Ascend/mindie/latest/mindie-service/conf/config.json如下：

 

{ 

    "Version" : "1.1.0", 

    "LogConfig" : 

    { 

        "logLevel" : "Info", 

        "logFileSize" : 20, 

        "logFileNum" : 20, 

        "logPath" : "logs/mindservice.log" 

    }, 

 

    "ServerConfig" : 

    { 

        "ipAddress" : "127.0.0.1", 

        "managementIpAddress" : "127.0.0.2", 

        "port" : 1025, 

        "managementPort" : 1026, 

        "metricsPort" : 1027, 

        "allowAllZeroIpListening" : false, 

        "maxLinkNum" : 1000, 

        "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" : true, 

        "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" 

    }, 

 

    "BackendConfig" : { 

        "backendName" : "mindieservice_llm_engine", 

        "modelInstanceNumber" : 1, 

        "npuDeviceIds" : [[0,1]], 

        "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", 

        "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" : 2560, 

            "maxInputTokenLen" : 2048, 

            "truncation" : false, 

            "ModelConfig" : [ 

                { 

                    "modelInstanceType" : "Standard", 

                    "modelName" : "qwen", 

                    "modelWeightPath" : "/DeepSeek-R1-Distill-Qwen-7B", 

                    "worldSize" : 2, 

                    "cpuMemSize" : 5, 

                    "npuMemSize" : -1, 

                    "backendType" : "atb", 

                    "trustRemoteCode" : false 

                } 

            ] 

        }, 

 

        "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 

        } 

    } 

}