华为计算微信公众号
昇腾AI开发者公众号
华为计算微博
华为计算今日头条
昇腾卡:2 * Atlas300iduo 驱动:24.1.rc2
固件:7.3.0.1.231
cann:8.0.RC2
mindie:1.0.RC2
配置文件mindie-server下面config.json
{ "OtherParam" : { "ResourceParam" : { "cacheBlockSize" : 128 }, "LogParam" : { "logLevel" : "Info", "logPath" : "logs/mindservice.log" }, "ServeParam" : { "ipAddress" : "192.168.39.46", "managementIpAddress" : "127.0.0.2", "port" : 1025, "managementPort" : 1026, "maxLinkNum" : 1000, "httpsEnabled" : false, "tlsCaPath" : "security/ca/", "tlsCaFile" : ["ca.pem"], "tlsCert" : "security/certs/server.pem", "tlsPk" : "security/keys/server.key.pem", "tlsPkPwd" : "security/pass/mindie_server_key_pwd.txt", "tlsCrl" : "security/certs/server_crl.pem", "managementTlsCaFile" : ["management_ca.pem"], "managementTlsCert" : "security/certs/management_server.pem", "managementTlsPk" : "security/keys/management_server.key.pem", "managementTlsPkPwd" : "security/pass/management_mindie_server_key_pwd.txt", "managementTlsCrl" : "security/certs/management_server_crl.pem", "kmcKsfMaster" : "tools/pmt/master/ksfa", "kmcKsfStandby" : "tools/pmt/standby/ksfb", "multiNodesInferPort" : 1120, "interNodeTLSEnabled" : true, "interNodeTlsCaFile" : "security/ca/ca.pem", "interNodeTlsCert" : "security/certs/server.pem", "interNodeTlsPk" : "security/keys/server.key.pem", "interNodeTlsPkPwd" : "security/pass/mindie_server_key_pwd.txt", "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa", "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb" } }, "WorkFlowParam" : { "TemplateParam" : { "templateType" : "Standard", "templateName" : "Standard_llama" } }, "ModelDeployParam" : { "engineName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "tokenizerProcessNumber" : 8, "maxSeqLen" : 4096, "npuDeviceIds" : [[0,1,2,3]], "multiNodesInferEnabled" : false, "ModelParam" : [ { "modelInstanceType" : "Standard", "modelName" : "llama_65b", "modelWeightPath" : "/workspce/modelzoo/yi-34b-chat", "worldSize" : 4, "cpuMemSize" : 5, "npuMemSize" : 8, "backendType" : "atb", "pluginParams" : "" } ] }, "ScheduleParam" : { "maxPrefillBatchSize" : 50, "maxPrefillTokens" : 8192, "prefillTimeMsPerReq" : 150, "prefillPolicyType" : 0, "decodeTimeMsPerReq" : 50, "decodePolicyType" : 0, "maxBatchSize" : 100, "maxIterTimes" : 1024, "maxPreemptCount" : 0, "supportSelectBatch" : false, "maxQueueDelayMicroseconds" : 5000 } }
芯片状态:
服务启动报错:
本帖最后由 匿名用户 于 2024/08/27 18:16:09 编辑
我要发帖子
昇腾卡:2 * Atlas300iduo
驱动:24.1.rc2
固件:7.3.0.1.231
cann:8.0.RC2
mindie:1.0.RC2
配置文件mindie-server下面config.json
{ "OtherParam" : { "ResourceParam" : { "cacheBlockSize" : 128 }, "LogParam" : { "logLevel" : "Info", "logPath" : "logs/mindservice.log" }, "ServeParam" : { "ipAddress" : "192.168.39.46", "managementIpAddress" : "127.0.0.2", "port" : 1025, "managementPort" : 1026, "maxLinkNum" : 1000, "httpsEnabled" : false, "tlsCaPath" : "security/ca/", "tlsCaFile" : ["ca.pem"], "tlsCert" : "security/certs/server.pem", "tlsPk" : "security/keys/server.key.pem", "tlsPkPwd" : "security/pass/mindie_server_key_pwd.txt", "tlsCrl" : "security/certs/server_crl.pem", "managementTlsCaFile" : ["management_ca.pem"], "managementTlsCert" : "security/certs/management_server.pem", "managementTlsPk" : "security/keys/management_server.key.pem", "managementTlsPkPwd" : "security/pass/management_mindie_server_key_pwd.txt", "managementTlsCrl" : "security/certs/management_server_crl.pem", "kmcKsfMaster" : "tools/pmt/master/ksfa", "kmcKsfStandby" : "tools/pmt/standby/ksfb", "multiNodesInferPort" : 1120, "interNodeTLSEnabled" : true, "interNodeTlsCaFile" : "security/ca/ca.pem", "interNodeTlsCert" : "security/certs/server.pem", "interNodeTlsPk" : "security/keys/server.key.pem", "interNodeTlsPkPwd" : "security/pass/mindie_server_key_pwd.txt", "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa", "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb" } }, "WorkFlowParam" : { "TemplateParam" : { "templateType" : "Standard", "templateName" : "Standard_llama" } }, "ModelDeployParam" : { "engineName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "tokenizerProcessNumber" : 8, "maxSeqLen" : 4096, "npuDeviceIds" : [[0,1,2,3]], "multiNodesInferEnabled" : false, "ModelParam" : [ { "modelInstanceType" : "Standard", "modelName" : "llama_65b", "modelWeightPath" : "/workspce/modelzoo/yi-34b-chat", "worldSize" : 4, "cpuMemSize" : 5, "npuMemSize" : 8, "backendType" : "atb", "pluginParams" : "" } ] }, "ScheduleParam" : { "maxPrefillBatchSize" : 50, "maxPrefillTokens" : 8192, "prefillTimeMsPerReq" : 150, "prefillPolicyType" : 0, "decodeTimeMsPerReq" : 50, "decodePolicyType" : 0, "maxBatchSize" : 100, "maxIterTimes" : 1024, "maxPreemptCount" : 0, "supportSelectBatch" : false, "maxQueueDelayMicroseconds" : 5000 } }芯片状态:
服务启动报错: