910b,一张卡,执行mindieservice_daemon报错, /usr/local/Ascend/mindie/latest/mindie-service/conf/config.json 参数配置
{
"Version" : "1.1.0",
"LogConfig" :
{
"logLevel" : "Info",
"logFileSize" : 20,
"logFileNum" : 20,
"logPath" : "logs/mindservice.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" : "qwen",
"modelWeightPath" : "/opt/deepseek",
"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
}
}
}
报错
2025-02-19 15:13:46,727 [ERROR] model.py:39 - [Model] >>> Exception:call aclnnInplaceZero failed, detail:EZ9999: Inner Error!
EZ9999: [PID: 5614] 2025-02-19-15:13:46.721.115 Parse dynamic kernel config fail.
TraceBack (most recent call last):
AclOpKernelInit failed opType
ZerosLike ADD_TO_LAUNCHER_LIST_AICORE failed.
[ERROR] 2025-02-19-15:13:46 (PID:5614, Device:0, RankID:-1) ERR01100 OPS call acl api failed
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/model_wrapper/model.py", line 37, in initialize
return self.python_model.initialize(config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/model_wrapper/standard_model.py", line 146, in initialize
self.generator = Generator(
^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 119, in __init__
self.warm_up(max_prefill_tokens, max_seq_len, max_input_len, max_iter_times, inference_mode)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 303, in warm_up
raise e
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 296, in warm_up
self._generate_inputs_warm_up_backend(input_metadata, inference_mode, dummy=True)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 378, in _generate_inputs_warm_up_backend
self.generator_backend.warm_up(model_inputs, inference_mode=inference_mode)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 198, in warm_up
super().warm_up(model_inputs)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 170, in warm_up
_ = self.forward(model_inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 38, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 153, in forward
logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 89, in forward
logits = self.forward_tensor(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 116, in forward_tensor
logits = self.model_runner.forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 193, in forward
return self.model.forward(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 452, in forward
self.init_ascend_weight()
File "/usr/local/Ascend/atb-models/atb_llm/models/qwen2/flash_causal_qwen2.py", line 150, in init_ascend_weight
weight_wrapper = self.get_weights()
^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/models/qwen2/flash_causal_qwen2.py", line 132, in get_weights
weight_wrapper = WeightWrapper(self.soc_info, self.tp_rank, attn_wrapper, mlp_wrapper)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/utils/data/weight_wrapper.py", line 49, in __init__
self.placeholder = torch.zeros(1, dtype=torch.float16, device="npu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: call aclnnInplaceZero failed, detail:EZ9999: Inner Error!
EZ9999: [PID: 5614] 2025-02-19-15:13:46.721.115 Parse dynamic kernel config fail.
TraceBack (most recent call last):
AclOpKernelInit failed opType
ZerosLike ADD_TO_LAUNCHER_LIST_AICORE failed.
[ERROR] 2025-02-19-15:13:46 (PID:5614, Device:0, RankID:-1) ERR01100 OPS call acl api failed
2025-02-19 15:13:46,731 [ERROR] model.py:42 - [Model] >>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0'}
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
Daemon is killing...
Killed
{
"Version" : "1.1.0",
"LogConfig" :
{
"logLevel" : "Info",
"logFileSize" : 20,
"logFileNum" : 20,
"logPath" : "logs/mindservice.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" : "qwen",
"modelWeightPath" : "/opt/deepseek",
"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
}
}
}
报错
2025-02-19 15:13:46,727 [ERROR] model.py:39 - [Model] >>> Exception:call aclnnInplaceZero failed, detail:EZ9999: Inner Error!
EZ9999: [PID: 5614] 2025-02-19-15:13:46.721.115 Parse dynamic kernel config fail.
TraceBack (most recent call last):
AclOpKernelInit failed opType
ZerosLike ADD_TO_LAUNCHER_LIST_AICORE failed.
[ERROR] 2025-02-19-15:13:46 (PID:5614, Device:0, RankID:-1) ERR01100 OPS call acl api failed
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/model_wrapper/model.py", line 37, in initialize
return self.python_model.initialize(config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/model_wrapper/standard_model.py", line 146, in initialize
self.generator = Generator(
^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 119, in __init__
self.warm_up(max_prefill_tokens, max_seq_len, max_input_len, max_iter_times, inference_mode)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 303, in warm_up
raise e
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 296, in warm_up
self._generate_inputs_warm_up_backend(input_metadata, inference_mode, dummy=True)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 378, in _generate_inputs_warm_up_backend
self.generator_backend.warm_up(model_inputs, inference_mode=inference_mode)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 198, in warm_up
super().warm_up(model_inputs)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 170, in warm_up
_ = self.forward(model_inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 38, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 153, in forward
logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 89, in forward
logits = self.forward_tensor(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 116, in forward_tensor
logits = self.model_runner.forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 193, in forward
return self.model.forward(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 452, in forward
self.init_ascend_weight()
File "/usr/local/Ascend/atb-models/atb_llm/models/qwen2/flash_causal_qwen2.py", line 150, in init_ascend_weight
weight_wrapper = self.get_weights()
^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/models/qwen2/flash_causal_qwen2.py", line 132, in get_weights
weight_wrapper = WeightWrapper(self.soc_info, self.tp_rank, attn_wrapper, mlp_wrapper)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/utils/data/weight_wrapper.py", line 49, in __init__
self.placeholder = torch.zeros(1, dtype=torch.float16, device="npu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: call aclnnInplaceZero failed, detail:EZ9999: Inner Error!
EZ9999: [PID: 5614] 2025-02-19-15:13:46.721.115 Parse dynamic kernel config fail.
TraceBack (most recent call last):
AclOpKernelInit failed opType
ZerosLike ADD_TO_LAUNCHER_LIST_AICORE failed.
[ERROR] 2025-02-19-15:13:46 (PID:5614, Device:0, RankID:-1) ERR01100 OPS call acl api failed
2025-02-19 15:13:46,731 [ERROR] model.py:42 - [Model] >>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0'}
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
Daemon is killing...
Killed