[root@bogon bin]# ./mindieservice_daemon
2025-05-23 10:30:21,669 [INFO] config.py:30 - model_config {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,670 [INFO] config.py:35 - do not init dmi config
2025-05-23 10:30:21,670 [INFO] standard_model.py:145 - rank id 0 get model config: {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,743 [INFO] config.py:30 - model_config {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '1', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '1', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '1', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,743 [INFO] config.py:35 - do not init dmi config
2025-05-23 10:30:21,743 [INFO] standard_model.py:145 - rank id 1 get model config: {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '1', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '1', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '1', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
[2025-05-23 10:30:26,607] [1509] [281467076002144] [llm] [INFO] [cpu_binding.py-212] : rank_id: 0, device_id: 0, numa_id: 1, shard_devices: [0, 1, 2, 3], cpus: [32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]
[2025-05-23 10:30:26,609] [1509] [281467076002144] [llm] [INFO] [cpu_binding.py-238] : process 1509, new_affinity is [32, 33, 34, 35, 36, 37, 38, 39], cpu count 8
[2025-05-23 10:30:26,676] [1511] [281467001815392] [llm] [INFO] [cpu_binding.py-212] : rank_id: 1, device_id: 1, numa_id: 1, shard_devices: [0, 1, 2, 3], cpus: [32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]
[2025-05-23 10:30:26,679] [1511] [281467001815392] [llm] [INFO] [cpu_binding.py-238] : process 1511, new_affinity is [40, 41, 42, 43, 44, 45, 46, 47], cpu count 8
[2025-05-23 10:30:27,233] [1509] [281467076002144] [llm] [INFO] [logging.py-331] : model_runner.quantize: None, model_runner.kv_quant_type: None, model_runner.fa_quant_type: None, model_runner.dtype: torch.float16
[root@bogon bin]# ./mindieservice_daemon
2025-05-23 10:30:21,669 [INFO] config.py:30 - model_config {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,670 [INFO] config.py:35 - do not init dmi config
2025-05-23 10:30:21,670 [INFO] standard_model.py:145 - rank id 0 get model config: {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '0', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,743 [INFO] config.py:30 - model_config {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '1', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '1', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '1', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
2025-05-23 10:30:21,743 [INFO] config.py:35 - do not init dmi config
2025-05-23 10:30:21,743 [INFO] standard_model.py:145 - rank id 1 get model config: {'backend_bin_path': '/usr/local/Ascend/mindie/1.0.0/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/1.0.0/mindie-service/logs/mindservice.log', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'dp': '0', 'ep': '0', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'interNodeKmcKsfMaster': 'tools/pmt/master/ksfa', 'interNodeKmcKsfStandby': 'tools/pmt/standby/ksfb', 'interNodeTLSEnabled': '1', 'interNodeTlsCaFiles': 'ca.pem,', 'interNodeTlsCaPath': 'security/grpc/ca/', 'interNodeTlsCert': 'security/grpc/certs/server.pem', 'interNodeTlsCrlFiles': 'server_crl.pem,', 'interNodeTlsCrlPath': 'security/grpc/certs/', 'interNodeTlsPk': 'security/grpc/keys/server.key.pem', 'interNodeTlsPkPwd': 'security/grpc/pass/mindie_server_key_pwd.txt', 'isMaster': '0', 'localIP': '', 'local_rank': '1', 'log_error': '1', 'log_file_num': '20', 'log_file_size': '20', 'log_info': '1', 'log_verbose': '0', 'log_warning': '1', 'masterIP': '', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_cut_policy': 'standard', 'model_id': '/home/TjDev/model/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'qwen', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '1', 'npu_device_ids': '0,1', 'npu_mem': '-1', 'pp': '0', 'rank': '1', 'slaveIPs': '', 'speculation_gamma': '0', 'tp': '0', 'trust_remote_code': '1', 'world_size': '2'}
[2025-05-23 10:30:26,607] [1509] [281467076002144] [llm] [INFO] [cpu_binding.py-212] : rank_id: 0, device_id: 0, numa_id: 1, shard_devices: [0, 1, 2, 3], cpus: [32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]
[2025-05-23 10:30:26,609] [1509] [281467076002144] [llm] [INFO] [cpu_binding.py-238] : process 1509, new_affinity is [32, 33, 34, 35, 36, 37, 38, 39], cpu count 8
[2025-05-23 10:30:26,676] [1511] [281467001815392] [llm] [INFO] [cpu_binding.py-212] : rank_id: 1, device_id: 1, numa_id: 1, shard_devices: [0, 1, 2, 3], cpus: [32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]
[2025-05-23 10:30:26,679] [1511] [281467001815392] [llm] [INFO] [cpu_binding.py-238] : process 1511, new_affinity is [40, 41, 42, 43, 44, 45, 46, 47], cpu count 8
[2025-05-23 10:30:27,233] [1509] [281467076002144] [llm] [INFO] [logging.py-331] : model_runner.quantize: None, model_runner.kv_quant_type: None, model_runner.fa_quant_type: None, model_runner.dtype: torch.float16