尝试启动推理服务，使用命令行 ./mindieservice_daemon后报错
LLMInferEngine failed to init LLMInferModels
ERR: Failed to init endpoint! Please check the service log or console output.
Killed
debug目录下log文件：
2025-02-19 09:59:06.966341 918 LLM log default format: [yyyy-mm-dd hh:mm:ss.uuuuuu][processid] [threadid] [llm] [loglevel][file:line] [error code] msg
[2025-02-19 09:59:06.966376] [917] [281473784016832] [llm] [INFO] [llm_manager_impl.cpp:70] LLMRuntime init success!
[2025-02-19 09:59:06.967394] [917] [281473784016832] [llm] [INFO] [model_deploy_config.cpp:130] ModelDeployConfig::pySonamelibpython3.11.so
[2025-02-19 09:59:12.379419] [917] [281473784016832] [llm] [INFO] [model_deploy_config.cpp:294] ModelDeployConfig::vocabSize=152064
[2025-02-19 09:59:12.383516] [917] [281473784016832] [llm] [INFO] [llm_manager_impl.cpp:195] InitModelConfig: maxSeqLen=2560, maxInputTokenLen=2048, g_truncation=0, g_truncLen=1
[2025-02-19 09:59:12.384944] [917] [281473784016832] [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
[2025-02-19 09:59:12.384965] [917] [281473784016832] [llm] [ERROR] [llm_infer_model.cpp:25] Init model instance failed.
一模一样的配置和流程，mindie1.0可以顺利Daemon start success。
MindIE版本：2.0
CANN版本：8.0.T63
容器启动命令：
docker run -it \
--name mindie2_3 \
--device=/dev/davinci0 \
--device=/dev/davinci_manager \
--device=/dev/devmm_svm \
--device=/dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/common \
-v /usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/driver/lib64/driver \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /etc/vnpu.cfg:/etc/vnpu.cfg \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /data1/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B:/mnt/models \
-v /home/scripts/:/home/scripts \
-p 8080:8080 \
mindie:2.0 bash
conf/config.json:
{
"Version" : "1.0.0",
"LogConfig" :
{
"logLevel" : "Info",
"logFileSize" : 20,
"logFileNum" : 20,
"logPath" : "logs/mindie-server.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]],
"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" : "mindie",
"modelWeightPath" : "/mnt/models",
"worldSize" : 1,
"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
}
}
}
点赞
收藏
回复
分享
举报
已解决
尝试启动推理服务，使用命令行 ./mindieservice_daemon后报错
LLMInferEngine failed to init LLMInferModels
ERR: Failed to init endpoint! Please check the service log or console output.
Killed
debug目录下log文件：
2025-02-19 09:59:06.966341 918 LLM log default format: [yyyy-mm-dd hh:mm:ss.uuuuuu][processid] [threadid] [llm] [loglevel][file:line] [error code] msg
[2025-02-19 09:59:06.966376] [917] [281473784016832] [llm] [INFO] [llm_manager_impl.cpp:70] LLMRuntime init success!
[2025-02-19 09:59:06.967394] [917] [281473784016832] [llm] [INFO] [model_deploy_config.cpp:130] ModelDeployConfig::pySonamelibpython3.11.so
[2025-02-19 09:59:12.379419] [917] [281473784016832] [llm] [INFO] [model_deploy_config.cpp:294] ModelDeployConfig::vocabSize=152064
[2025-02-19 09:59:12.383516] [917] [281473784016832] [llm] [INFO] [llm_manager_impl.cpp:195] InitModelConfig: maxSeqLen=2560, maxInputTokenLen=2048, g_truncation=0, g_truncLen=1
[2025-02-19 09:59:12.384944] [917] [281473784016832] [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
[2025-02-19 09:59:12.384965] [917] [281473784016832] [llm] [ERROR] [llm_infer_model.cpp:25] Init model instance failed.
一模一样的配置和流程，mindie1.0可以顺利Daemon start success。
MindIE版本：2.0
CANN版本：8.0.T63
容器启动命令：
docker run -it \
--name mindie2_3 \
--device=/dev/davinci0 \
--device=/dev/davinci_manager \
--device=/dev/devmm_svm \
--device=/dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/common \
-v /usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/driver/lib64/driver \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /etc/vnpu.cfg:/etc/vnpu.cfg \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /data1/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B:/mnt/models \
-v /home/scripts/:/home/scripts \
-p 8080:8080 \
mindie:2.0 bash
conf/config.json:
{ "Version" : "1.0.0", "LogConfig" : { "logLevel" : "Info", "logFileSize" : 20, "logFileNum" : 20, "logPath" : "logs/mindie-server.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]], "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" : "mindie", "modelWeightPath" : "/mnt/models", "worldSize" : 1, "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 } } }