使用mindie 2.0.T3起服务时遇到报错 [mindie-serverdebug] Permission denied和[mindie-serversecurity] Permission denied
收藏回复举报
使用mindie 2.0.T3起服务时遇到报错 [mindie-serverdebug] Permission denied和[mindie-serversecurity] Permission denied
t('forum.solved') 已解决
新人帖
发表于2025-02-16 22:31:32
0 查看

背景: 使用华为云modelarts standard基于以下镜像 swr.cn-southwest-2.myhuaweicloud.com/ei-mindie/mindie:2.0.T3-800I-A2-py311-openeuler24.03-lts 通过在dockerfile中写入指令创建用户ma-user,并给予sudo权限创建了新的镜像,基于此镜像启动了两个8卡910B3的作业,尝试部署deepseek-r1 w8a8量化

根据以下文档进行了操作和配置

https://support.huaweicloud.com/bestpractice-modelarts/modelarts_ds_infer_0006.html

config.json的内容如下

{
    "Version": "1.0.0",
    "LogConfig": {
        "logLevel": "Info",
        "logFileSize": 20,
        "logFileNum": 20,
        "logPath": "logs/mindie-server.log"
    },
    "ServerConfig": {
        "ipAddress": "192.168.179.164",
        "managementIpAddress": "192.168.179.164",
        "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": false,
        "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,
                2,
                3,
                4,
                5,
                6,
                7
            ]
        ],
        "tokenizerProcessNumber": 8,
        "multiNodesInferEnabled": true,
        "multiNodesInferPort": 1120,
        "interNodeTLSEnabled": false,
        "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": "DeepSeek-R1",
                    "modelWeightPath": "/home/ma-user/modelarts/work/model/deepseekR1-w8a8",
                    "worldSize": 8,
                    "cpuMemSize": 5,
                    "npuMemSize": -1,
                    "backendType": "atb",
                    "trustRemoteCode": false,
                    "world_size": 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
        }
    }
}

运行

./bin/mindieservice_daemon

启动服务时,终端提示报错

[ma-user@ma-job-d016a8ef-42ee-4a25-b346-2d7639a56dfb-worker-0 mindie-service]$ ./bin/mindieservice_daemon
Start to parse ranktable file
Finished parsing ranktable file.
Update worldSize and npuDeviceIds of backend config successfully for Multi Nodes Inference.
[*** LOG ERROR #0001 ***] [2025-02-16 22:14:27] [mindie-serverdebug] Permission denied
LLMInferEngine failed to init LLMInferModels
[*** LOG ERROR #0008 ***] [2025-02-16 22:14:38] [mindie-serversecurity] Permission denied
ERR: Failed to init endpoint! Please check the service log or console output.
Killed

其他日志文件内容分别如下

mindie-server_1104267_202502162214.log

[2025-02-16 22:14:21.712+08:00] [1104267] [1104279] [mindie-server] ===init log===
[2025-02-16 22:14:27.499+08:00] [1104267] [1104279] [mindie-server] ===init log===

mindie-llm_c_1104267_20250216221421

2025-02-16 22:14:21.767519 1104279 LLM log default format: [yyyy-mm-dd hh:mm:ss.uuuuuu][processid] [threadid] [llm] [loglevel][file:line] [error code] msg
[2025-02-16 22:14:21.767544] [1104267] [281473167257536] [llm] [INFO] [llm_manager_impl.cpp:70] LLMRuntime init success!
[2025-02-16 22:14:21.769264] [1104267] [281473167257536] [llm] [INFO] [model_deploy_config.cpp:130] ModelDeployConfig::pySonamelibpython3.11.so
[2025-02-16 22:14:27.479232] [1104267] [281473167257536] [llm] [INFO] [model_deploy_config.cpp:294] ModelDeployConfig::vocabSize=129280
[2025-02-16 22:14:27.498464] [1104267] [281473167257536] [llm] [INFO] [llm_manager_impl.cpp:195] InitModelConfig: maxSeqLen=2560, maxInputTokenLen=2048, g_truncation=0, g_truncLen=1
[2025-02-16 22:14:27.499902] [1104267] [281473167257536] [llm] [ERROR] [llm_infer_model_instance.cpp:47] [MIE05E030001] Initialize modelBackends_ failed, export MINDIE_LLM_PYTHON_LOG_TO_STDOUT=1 export MINDIE_LLM_PYTHON_LOG_TO_FILE=1 to find error in pythonlog
[2025-02-16 22:14:27.499931] [1104267] [281473167257536] [llm] [ERROR] [llm_infer_model.cpp:25] Init model instance failed.

已经按照要求配置了 export MINDIE_LLM_PYTHON_LOG_TO_STDOUT=1 export MINDIE_LLM_PYTHON_LOG_TO_FILE=1 但是能收集到的报错日志只有以上这些,请问能否定位permission denied的文件的位置?

我要发帖子