2.1.RC1-300I-Duo-py311-openeuler24.03-lts在300iDUO卡部署Qwen3-30B-A3B模型报错_MindIE_昇腾论坛

# 2.1.RC1-300I-Duo-py311-openeuler24.03-lts在300iDUO卡部署Qwen3-30B-A3B模型报错_MindIE_昇腾论坛

## 概述

本文档基于昇腾社区论坛帖子生成的技术教程。

**原始链接**: https://www.hiascend.com/forum/thread-0297189844618201158-1-1.html

**生成时间**: 2025-08-27 10:33:56

---

## 问题描述

容器启动命令 docker run -p 11025:11025 -itd -u root --ipc=host --net=host --privileged \ --name ceshiduo-new-qw30a3b \ --ipc=host \ --device=/dev/davinci0 \ --device=/dev/davinci1 \ --device=/dev/davinci_manager \ --device=/dev/devmm_svm \ --device=/dev/hisi_hdc \ -v /usr/local/dcmi:/usr/local/dcmi \ -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \ -v /usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/common \ -v /usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/driver/lib64/driver \ -v /etc/ascend_install.info:/etc/ascend_install.info \ -v /etc/vnpu.cfg:/etc/vnpu.cfg \ -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \ -v /data1/models/Qwen3-30B-A3B:/data1/models/Qwen3-30B-A3B \ swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:2.1.RC1-300I-Duo-py311-openeuler24.03-lts /bin/bash config.xml配置文件 { "Version" : "1.0.0", "ServerConfig" : { "ipAddress" : "127.0.0.1", "managementIpAddress" : "127.0.0.2", "port" : 11025, "managementPort" : 110...

## 相关图片

### 图片 1

![cke_162.png](https://fileserver.developer.huaweicloud.com/FileServer/getFile/cmtybbs/374/0dd/9ab/0390344c6e3740dd9ab7a6313c64be8d.20250819072540.58374769141239499503696907606506:20250827013850:2400:EB2170844F21E501DF70F655EB7EE43A3335FD98E0E7BFFFA648D45A74913090.png)

**图片地址**: https://fileserver.developer.huaweicloud.com/FileServer/getFile/cmtybbs/374/0dd/9ab/0390344c6e3740dd9ab7a6313c64be8d.20250819072540.58374769141239499503696907606506:20250827013850:2400:EB2170844F21E501DF70F655EB7EE43A3335FD98E0E7BFFFA648D45A74913090.png

**图片描述**: cke_162.png

## 完整内容

容器启动命令 docker run -p 11025:11025 -itd -u root --ipc=host --net=host --privileged \ --name ceshiduo-new-qw30a3b \ --ipc=host \ --device=/dev/davinci0 \ --device=/dev/davinci1 \ --device=/dev/davinci_manager \ --device=/dev/devmm_svm \ --device=/dev/hisi_hdc \ -v /usr/local/dcmi:/usr/local/dcmi \ -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \ -v /usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/common \ -v /usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/driver/lib64/driver \ -v /etc/ascend_install.info:/etc/ascend_install.info \ -v /etc/vnpu.cfg:/etc/vnpu.cfg \ -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \ -v /data1/models/Qwen3-30B-A3B:/data1/models/Qwen3-30B-A3B \ swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:2.1.RC1-300I-Duo-py311-openeuler24.03-lts /bin/bash config.xml配置文件 { "Version" : "1.0.0", "ServerConfig" : { "ipAddress" : "127.0.0.1", "managementIpAddress" : "127.0.0.2", "port" : 11025, "managementPort" : 11026, "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", "tokenTimeout" : 600, "e2eTimeout" : 600, "distDPServerEnabled":false }, "BackendConfig" : { "backendName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "npuDeviceIds" : [[0,1]], "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" : "Qwen3-30B-A3B", "modelWeightPath" : "/data1/models/Qwen3-30B-A3B", "worldSize" : 2, "cpuMemSize" : 5, "npuMemSize" : 2, "backendType" : "atb", "trustRemoteCode" : false, "async_scheduler_wait_time": 120, "kv_trans_timeout": 10, "kv_link_timeout": 1080 } ] }, "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 } } } transformers已经升级到4.51.0 pip install transformers==4.51.0 错误信息如下 [2025-08-06 14:23:58.630+08:00] [1163] [1163] [batchscheduler] [INFO] [slave_IPC_communicator.cpp:1175] : [model_backend] Slave communicator launch threads success. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [model.py:83] : [python thread: infer] launch do_inference thread. thread_num: 1 [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:19] : model_config {'asyncBatchscheduler': 'false', 'async_infer': 'false', 'async_scheduler_wait_time': '120', 'backend_bin_path': '/usr/local/Ascend/mindie/2.1.RC1/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/2.1.RC1/mindie-service/~/mindie/log/', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'distributed_enable': 'false', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'infer_mode': 'standard', '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', 'is_dmi_infer': '0', 'kv_link_timeout': '1080', 'kv_trans_timeout': '10', '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_batch_size': '200', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_id': '/data1/models/Qwen3-30B-A3B', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'Qwen3-30B-A3B', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '2', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'threadNum': '1', 'trust_remote_code': '0', 'world_size': '2'} [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item local_rank value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item infer_mode value is standard. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item model_instance_type value is Standard. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item speculation_gamma value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item backend_type value is atb. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named plugin_params, use default value . [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item plugin_params value is . [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named tp, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item tp value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named pp, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item pp value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named ep, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item ep value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named dp, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item dp value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named es, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item es value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named sp, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item sp value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:75] : There is no item named cp, use default value 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item cp value is 1. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item model_id value is /data1/models/Qwen3-30B-A3B. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item local_rank value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item rank value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item globalRankIds value is . [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item globalWorldSize value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item world_size value is 2. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item npu_device_id value is 0. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:91] : The list item npu_device_ids value is ['0', '1']. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item cpu_mem value is 5. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item npu_mem value is 2. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item max_seq_len value is 2560. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item max_iter_times value is 512. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item max_prefill_tokens value is 8192. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item block_size value is 128. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:79] : The item distributed_enable value is false. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [config.py:30] : >>model_config after initialize {'asyncBatchscheduler': 'false', 'async_infer': 'false', 'async_scheduler_wait_time': '120', 'backend_bin_path': '/usr/local/Ascend/mindie/2.1.RC1/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/2.1.RC1/mindie-service/~/mindie/log/', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'distributed_enable': 'false', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'infer_mode': 'standard', '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', 'is_dmi_infer': '0', 'kv_link_timeout': '1080', 'kv_trans_timeout': '10', '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_batch_size': '200', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_id': '/data1/models/Qwen3-30B-A3B', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'Qwen3-30B-A3B', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '2', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'threadNum': '1', 'trust_remote_code': '0', 'world_size': '2'} [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [model.py:40] : init base config [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [metrics.py:56] : profiling is disenabled. [2025-08-06 14:24:04.006+0800] [1163] [281472845869408] [batchscheduler] [INFO] [standard_model.py:132] : global rank id 0 get model config: {'asyncBatchscheduler': 'false', 'async_infer': 'false', 'async_scheduler_wait_time': '120', 'backend_bin_path': '/usr/local/Ascend/mindie/2.1.RC1/mindie-llm/bin/', 'backend_log_file': '/usr/local/Ascend/mindie/2.1.RC1/mindie-service/~/mindie/log/', 'backend_modelInstance_id': '0', 'backend_type': 'atb', 'block_size': '128', 'cpu_mem': '5', 'deploy_type': 'INTER_PROCESS', 'distributed_enable': 'false', 'executor_type': 'LLM_EXECUTOR_PYTHON', 'globalRankIds': '', 'globalWorldSize': '0', 'infer_mode': 'standard', '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', 'is_dmi_infer': '0', 'kv_link_timeout': '1080', 'kv_trans_timeout': '10', '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_batch_size': '200', 'max_input_len': '2048', 'max_iter_times': '512', 'max_prefill_tokens': '8192', 'max_seq_len': '2560', 'model_id': '/data1/models/Qwen3-30B-A3B', 'model_instance_number': '1', 'model_instance_type': 'Standard', 'model_name': 'Qwen3-30B-A3B', 'multiNodesInferEnabled': '0', 'multiNodesInferPort': '1120', 'npu_device_id': '0', 'npu_device_ids': '0,1', 'npu_mem': '2', 'rank': '0', 'slaveIPs': '', 'speculation_gamma': '0', 'threadNum': '1', 'trust_remote_code': '0', 'world_size': '2'} [2025-08-06 14:25:58.006+0800] [1163] [281472845869408] [batchscheduler] [ERROR] [model.py:61] : [Model] >>> Exception:Execute fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document. Traceback (most recent call last): File "/usr/local/lib/python3.11/site-packages/model_wrapper/model.py", line 59, in initialize return self.python_model.initialize(config)  File "/usr/local/lib/python3.11/site-packages/model_wrapper/standard_model.py", line 133, in initialize self.generator = Generator(  File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 299, in __init__ self.cache_manager = self.warm_up(  File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 453, in warm_up cache_manager = self.__warmup_specified(max_prefill_tokens, max_seq_len, max_input_len, max_iter_times)  File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 648, in __warmup_specified self.__execute_warm_up(cache_manager, input_metadata, self.inference_mode) File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 508, in __execute_warm_up raise e File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 499, in __execute_warm_up self.generator_backend._warm_up(model_inputs, inference_mode=self.inference_mode, File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 570, in _warm_up super()._warm_up(model_inputs, **kwargs) File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 247, in _warm_up logits = self.forward(model_inputs, **kwargs)  File "/usr/local/lib/python3.11/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 69, in wrapper return func(*args, **kwargs)  File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 230, in forward logits = self._forward(model_inputs, **kwargs)  File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 621, 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 125, in forward result = self.forward_from_model_inputs(model_inputs, npu_cache, **kwargs)  File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 197, in forward_from_model_inputs result = self.forward_tensor(  File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 237, in forward_tensor result = self.model_runner.forward(  File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 310, in forward res = self.model.forward(**kwargs)  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 536, in forward logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 467, in execute_ascend_operator acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)  RuntimeError: Execute fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document. 搞定了吗我们开始部Qwen3-Code-30B-A3B 没有解决 8月14日 mindie 偷偷更新了重新下版本号什么的都没变 Qwen3-30B-A3B 可以部署了300I-Duo要2物理卡 至于Qwen3-Code-30B-A3B 还是不支持无限吃内存 300I-DUO 1张卡的内存应该足够部署呢为什么还是需要2张物理卡呢 1官方发布 https://www.hiascend.com/software/mindie/modellist 支持清单中写的 2本地实际1张卡2张卡 验证过 能看下你配置吗 我用最新镜像 单卡duo还是报错一样的错误 "npuDeviceIds" : [[4,5,6,7]], { "modelInstanceType" : "Standard", "modelName" : "qwen3-30b-a3b", "modelWeightPath" : "/modelfile", "worldSize" : 4, "cpuMemSize" : 20, "npuMemSize" : 5, "backendType" : "atb", "trustRemoteCode" : true } 公司只有单卡了验证不了不知道W8A8单卡能跑不非常谢谢

---

## 技术要点总结

基于以上内容，主要技术要点包括：

1. **问题类型**: 错误处理
2. **涉及技术**: HTTPS, NPU, Docker, MindIE, 昇腾, AI
3. **解决方案**: 请参考完整内容中的解决方案

## 相关资源

- 昇腾社区: https://www.hiascend.com/
- 昇腾论坛: https://www.hiascend.com/forum/

---

*本文档由AI自动生成，仅供参考。如有疑问，请参考原始帖子。*