RuntimeError: The Inner error is reported as above. The process exits for this inner error, and the current working operator name is Qwen25VL_VIT_graph.
Since the operator is called asynchronously, the stacktrace may be inaccurate. If you want to get the accurate stacktrace, please set the environment variable ASCEND_LAUNCH_BLOCKING=1.
Note: ASCEND_LAUNCH_BLOCKING=1 will force ops to run in synchronous mode, resulting in performance degradation. Please unset ASCEND_LAUNCH_BLOCKING in time after debugging.
环境信息:
npu型号:300i pro (24G)
驱动版本:25.2.0
固件版本:7.7.0.6.236
docker mindie镜像版本:2.1.RC1-300I-Duo-py311-openeuler24.03-lts
模型:qwen2.5-vl-3b
异常情况描述:
mindie可以正常启动模型,
当启动配置中,制定了worldsize=1,调用推理可以成功
当启动配置中,制定了worldsize=2,调用推理报错
报错信息:
config.json配置
{ "Version" : "1.0.0", "ServerConfig" : { "ipAddress" : "0.0.0.0", "managementIpAddress" : "127.0.0.1", "port" : 1025, "managementPort" : 1026, "metricsPort" : 1027, "allowAllZeroIpListening" : true, "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", "tokenTimeout" : 600, "e2eTimeout" : 600, "distDPServerEnabled":false }, "BackendConfig" : { "backendName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "npuDeviceIds" : [[0,1]], "tokenizerProcessNumber" : 8, "multiNodesInferEnabled" : false, "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" : 8192, "maxInputTokenLen" : 8192, "truncation" : false, "ModelConfig" : [ { "modelInstanceType" : "Standard", "modelName" : "qwen2.5-vl-3b", "modelWeightPath" : "/model_weights", "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" : 4096, "maxPreemptCount" : 0, "supportSelectBatch" : false, "maxQueueDelayMicroseconds" : 5000 } } }