acl.mdl.load_from_file()加载om模型失败,错误码500002
收藏回复举报
acl.mdl.load_from_file()加载om模型失败,错误码500002
t('forum.solved') 已解决
新人帖
发表于2024-12-31 15:13:55
0 查看

日志如下:

2024-12-31T07:06:22.266738457Z [EVENT] ASCENDCL(1271558,python):2024-12-31-15:06:22.266.672 [acl_resource_manager.cpp:90]1271558 GetRuntimeV2Env: runtime v2 flag : model flag = 1, singleOp flag = 1

2024-12-31T07:06:22.270944532Z [EVENT] PROFILING(1271558,python):2024-12-31-15:06:22.270.870 [prof_atls_plugin.cpp:160] >>> (tid:1271558) Module[48] register callback of ctrl handle.

2024-12-31T07:06:22.270951428Z [EVENT] PROFILING(1271558,python):2024-12-31-15:06:22.270.901 [prof_atls_plugin.cpp:160] >>> (tid:1271558) Module[45] register callback of ctrl handle.

2024-12-31T07:06:22.463699680Z [EVENT] PROFILING(1271558,python):2024-12-31-15:06:22.463.566 [msprof_callback_impl.cpp:79] >>> (tid:1271558) MsprofCtrlCallback called, type: 255

2024-12-31T07:06:22.463814340Z [EVENT] PROFILING(1271558,python):2024-12-31-15:06:22.463.761 [ai_drv_dev_api.cpp:333] >>> (tid:1271558) Succeeded to DrvGetApiVersion version: 0x72317

2024-12-31T07:06:22.463889604Z [EVENT] RUNTIME(1271558,python):2024-12-31-15:06:22.463.852 [runtime.cc:4393] 1271558 GetVisibleDevices: ASCEND_RT_VISIBLE_DEVICES param was not set

2024-12-31T07:06:22.465259409Z [EVENT] PROFILING(1271558,python):2024-12-31-15:06:22.465.190 [prof_atls_plugin.cpp:160] >>> (tid:1271558) Module[7] register callback of ctrl handle.

2024-12-31T07:06:22.465804338Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.465.750 [process_mode_manager.cpp:107][OpenProcess][tid:1271558] [ProcessModeManager] enter into open process deviceId[0] rankSize[0]

2024-12-31T07:06:22.466551872Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.466.498 [process_mode_manager.cpp:377][InitTsdClient][tid:1271558] [TsdClient] deviceId[0] begin to init hdc client

2024-12-31T07:06:22.466753815Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.466.701 [version_verify.cpp:34][SetVersionInfo][tid:1271558] VersionVerify: send client version to server

2024-12-31T07:06:22.466757202Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.466.717 [version_verify.cpp:51][SetVersionInfo][tid:1271558] send feature_info:{msg_type:35, features:{check before send aicpu package,}}

2024-12-31T07:06:22.466759675Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.466.722 [version_verify.cpp:51][SetVersionInfo][tid:1271558] send feature_info:{msg_type:37, features:{check before send open qs message,}}

2024-12-31T07:06:22.467583476Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.529 [version_verify.cpp:67][PeerVersionCheck][tid:1271558] VersionVerify: Check client version info, server[1230], client[1230]

2024-12-31T07:06:22.467588025Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.539 [version_verify.cpp:88][ParseVersionInfo][tid:1271558] VersionVerify: pass client version info success

2024-12-31T07:06:22.467590640Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.543 [hdc_client.cpp:276][CheckHdcConnection][tid:1271558] Service[2] create hdc success

2024-12-31T07:06:22.467592963Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.549 [version_verify.cpp:121][SpecialFeatureCheck][tid:1271558] VersionVerify: new type[35], supported

2024-12-31T07:06:22.467679417Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.607 [process_mode_manager.cpp:748][GetDeviceCheckCode][tid:1271558] [TsdClient][deviceId=0] [sessionId=1]wait package info respond

2024-12-31T07:06:22.467935108Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.467.888 [process_mode_manager.cpp:377][InitTsdClient][tid:1271558] [TsdClient] deviceId[0] begin to init hdc client

2024-12-31T07:06:22.468097659Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.051 [version_verify.cpp:34][SetVersionInfo][tid:1271558] VersionVerify: send client version to server

2024-12-31T07:06:22.468100973Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.060 [version_verify.cpp:51][SetVersionInfo][tid:1271558] send feature_info:{msg_type:35, features:{check before send aicpu package,}}

2024-12-31T07:06:22.468103426Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.064 [version_verify.cpp:51][SetVersionInfo][tid:1271558] send feature_info:{msg_type:37, features:{check before send open qs message,}}

2024-12-31T07:06:22.468604526Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.535 [version_verify.cpp:67][PeerVersionCheck][tid:1271558] VersionVerify: Check client version info, server[1230], client[1230]

2024-12-31T07:06:22.468610850Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.543 [version_verify.cpp:88][ParseVersionInfo][tid:1271558] VersionVerify: pass client version info success

2024-12-31T07:06:22.468613616Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.547 [hdc_client.cpp:276][CheckHdcConnection][tid:1271558] Service[2] create hdc success

2024-12-31T07:06:22.468615965Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.551 [process_mode_manager.cpp:424][ConstructOpenMsg][tid:1271558] [TsdClient] tsd get process sign successfully, procpid[1271558] signSize[48]

2024-12-31T07:06:22.468618486Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.556 [version_verify.cpp:113][SpecialFeatureCheck][tid:1271558] VersionVerify: previous type[6], supported

2024-12-31T07:06:22.468620852Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.468.563 [process_mode_manager.cpp:124][OpenProcess][tid:1271558] [ProcessModeManager] deviceId[0] sessionId[1] rankSize[0], wait sub process start respond

2024-12-31T07:06:22.859830405Z [EVENT] DRV(1271558,python):2024-12-31-15:06:22.859.711 [ascend][curpid: 1271558, 1271558][drv][devmm][devmm_setup_device 88]DrvMemDeviceOpen. (devid=0)

2024-12-31T07:06:22.860297255Z [EVENT] DRV(1271558,python):2024-12-31-15:06:22.860.218 [ascend][curpid: 1271558, 1271558][drv][devmm][devmm_ioctl_init_process 394]Init_process details. (hostpid=1271558)

2024-12-31T07:06:22.860572971Z [EVENT] DRV(1271558,python):2024-12-31-15:06:22.860.513 [ascend][curpid: 1271558, 1271558][drv][devmm][share_log_read_in_single_module 649]Setup device succeeded. (logical_devid=0; devid=4; vfid=0; hostpid=1271558; devpid=17264)

2024-12-31T07:06:22.861372307Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.861.304 [stub_process_mode_nowin.cpp:61][ProcessQueueForMdc][tid:1271558] [TsdClient] it is unnecessary of current mode[0] chiptype[2] to grant queue auth to aicpusd

2024-12-31T07:06:22.861377373Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.861.316 [stub_process_mode_nowin.cpp:99][OpenInHost][tid:1271558] enter into OpenInHost deviceid[0]

2024-12-31T07:06:22.861379937Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.861.321 [stub_process_mode_nowin.cpp:103][OpenInHost][tid:1271558] host cpu not support

2024-12-31T07:06:22.861382548Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.861.325 [process_mode_manager.cpp:154][OpenProcess][tid:1271558] [TsdClient][deviceId=0] [sessionId=1] start hccp and computer process success

2024-12-31T07:06:22.861824067Z [EVENT] DRV(1271558,python):2024-12-31-15:06:22.861.763 [ascend][curpid: 1271558, 1271558][drv][devmm][devmm_setup_device 88]DrvMemDeviceOpen. (devid=0)

2024-12-31T07:06:22.902987163Z [EVENT] RUNTIME(1271558,python):2024-12-31-15:06:22.902.920 [device.cc:341] 1271558 Init: isDoubledie:0, topologytype:0

2024-12-31T07:06:22.927279535Z [EVENT] RUNTIME(1271558,python):2024-12-31-15:06:22.927.153 [npu_driver.cc:5320] 1271880 GetDeviceStatus: GetDeviceStatus status=1.

2024-12-31T07:06:22.928508698Z [EVENT] TDT(1271558,python):2024-12-31-15:06:22.928.400 [client_manager.cpp:157][SetProfilingCallback][tid:1271558] [TsdClient] set profiling callback success

2024-12-31T07:06:22.972979594Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.830 [model_utils.cc:1299]1271558 GetHbmFeatureMapMemInfo: ErrorNo: 4294967295(failed) [LOAD][DEFAULT]Assert (sub_memory_info.size() == 3U) failed, expect 3 actual 4

2024-12-31T07:06:22.973007516Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.869 [model_utils.cc:1314]1271558 GetAllMemoryTypeSize: ErrorNo: 4294967295(failed) [LOAD][DEFAULT]Assert ((GetHbmFeatureMapMemInfo(ge_model, all_mem_info)) == ge::SUCCESS) failed

2024-12-31T07:06:22.973011437Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.880 [model_utils.cc:1272]1271558 InitRuntimeParams: ErrorNo: 4294967295(failed) [LOAD][DEFAULT]Assert (total_hbm_size == (static_cast<int64_t>(runtime_param.mem_size) - runtime_param.zero_copy_size)) failed, expect 18754048 actual 0

2024-12-31T07:06:22.973017239Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.888 [davinci_model.cc:451]1271558 InitRuntimeParams: ErrorNo: 4294967295(failed) [LOAD][DEFAULT]Assert ((ModelUtils::InitRuntimeParams(ge_model_, runtime_param_, device_id_)) == ge::SUCCESS) failed

2024-12-31T07:06:22.973020059Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.895 [davinci_model.cc:640]1271558 Init: ErrorNo: 4294967295(failed) [LOAD][DEFAULT]Assert ((InitRuntimeParams()) == ge::SUCCESS) failed

2024-12-31T07:06:22.973022468Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.972.900 [model_manager.cc:1203]1271558 LoadModelOffline: ErrorNo: 4294967295(failed) [LOAD][DEFAULT][Init][DavinciModel] failed, ret:1343225857.

2024-12-31T07:06:22.973854211Z [ERROR] GE(1271558,python):2024-12-31-15:06:22.973.773 [graph_loader.cc:143]1271558 LoadModelFromData: ErrorNo: 1343225857(Parameter's invalid!) [LOAD][DEFAULT][Load][Model] failed, model_id:1.

2024-12-31T07:06:22.973867046Z [ERROR] ASCENDCL(1271558,python):2024-12-31-15:06:22.973.796 [model.cpp:280]1271558 ModelLoadFromFileWithMem: [LOAD][DEFAULT][Model][FromData]load model from data failed, ge result[1343225857]

2024-12-31T07:06:22.974365789Z [ERROR] ASCENDCL(1271558,python):2024-12-31-15:06:22.974.301 [model.cpp:1628]1271558 aclmdlLoadFromFile: [LOAD][DEFAULT]Load model from file failed!

本帖最后由 匿名用户2024/12/31 16:26:09 编辑

我要发帖子