华为计算微信公众号
昇腾AI开发者公众号
华为计算微博
华为计算今日头条
环境是华为昇腾910B算力卡 + openEuler 24.03 LTS环境，基础镜像是2.1.RC1-800I-A2-py311-openeuler24.03-lts，推理qwen2.5-vl报错：
[root@b4364c747db8 workspace]# cd /usr/local/Ascend/mindie/latest/mindie-service/bin ./mindieservice_daemon 2025-08-11 10:10:49.521 2025 LLM log default format: [yyyy-mm-dd hh:mm:ss.uuuuuu] [processid] [threadid] [llm] [loglevel] [file:line] [status code] msg [2025-08-11 10:10:49.521] [2023] [281461834706560] [llm] [INFO] [llm_manager_impl.cpp:76] LLMRuntime init success! [2025-08-11 10:10:55.166+08:00] [2023] [2025] [server] [WARN] [llm_daemon.cpp:74] : [MIE04W01011A] [daemon] Received exit signal[17] [2025-08-11 10:10:55.166+08:00] [2023] [2025] [server] [WARN] [llm_daemon.cpp:84] : [MIE04W010109] [daemon] Process 2157 exited normally with status 0 [2025-08-11 10:10:58.240+08:00] [2023] [2025] [server] [WARN] [llm_daemon.cpp:74] : [MIE04W01011A] [daemon] Received exit signal[17] Segmentation fault (core dumped)
包环境如下：
Package Version --------------------------------- ---------------------- absl-py 2.1.0 accelerate 1.8.1 addict 2.4.0 aiofiles 24.1.0 aiohappyeyeballs 2.6.1 aiohttp 3.12.14 aiosignal 1.4.0 airportsdata 20250706 ais-bench-benchmark 0.0.1 aliyun-python-sdk-core 2.16.0 aliyun-python-sdk-kms 2.16.5 annotated-types 0.7.0 antlr4-python3-runtime 4.13.2 anyio 4.9.0 ascendie 2.1rc1 astor 0.8.1 astunparse 1.6.3 attrdict 2.0.1 attrs 24.2.0 auto_tune 0.1.0 av 13.1.0 blake3 1.0.5 Brotli 1.1.0 certifi 2024.8.30 cffi 1.17.1 charset-normalizer 3.3.2 click 8.1.7 cloudpickle 3.0.0 cmake 4.0.3 colorama 0.4.6 compressed-tensors 0.9.1 confluent-kafka 2.10.1 contourpy 1.3.0 cpm-kernels 1.0.11 crcmod 1.7 cryptography 45.0.5 cycler 0.12.1 dacite 1.6.0 daemonize 2.5.0 dataflow 0.0.1 datasets 3.0.0 decorator 5.1.1 depyf 0.18.0 dill 0.3.8 diskcache 5.6.3 distro 1.9.0 easydict 1.13 einops 0.8.1 et-xmlfile 1.1.0 evaluate 0.4.5 fastapi 0.116.1 ffmpy 0.6.0 filelock 3.16.1 fire 0.7.0 flatbuffers 25.2.10 fonttools 4.54.1 frozenlist 1.7.0 fsspec 2024.6.1 func-timeout 4.3.5 future 1.0.0 fuzzywuzzy 0.18.0 gast 0.6.0 gevent 24.2.1 geventhttpclient 2.3.1 gguf 0.10.0 google-pasta 0.2.0 gpg 1.21.0 gradio 5.38.0 gradio_client 1.11.0 greenlet 3.1.1 groovy 0.1.2 grpcio 1.66.1 h11 0.16.0 h5py 3.14.0 hccl 0.1.0 hccl_parser 0.1 httpcore 1.0.9 httpx 0.27.2 huggingface-hub 0.27.1 human-eval 1.0.3 icetk 0.0.4 idna 3.10 immutabledict 4.2.1 importlib_metadata 8.7.0 interegular 0.3.3 jieba 0.42.1 Jinja2 3.1.4 jiter 0.10.0 jmespath 0.10.0 joblib 1.4.2 json5 0.12.0 jsonlines 4.0.0 jsonschema 4.25.0 jsonschema-specifications 2025.4.1 keras 3.10.0 kiwisolver 1.4.7 langdetect 1.0.9 lark 1.2.2 latex2mathml 3.77.0 latex2sympy2_extended 1.0.6 Levenshtein 0.27.1 libclang 18.1.1 libcomps 0.1.19 llm_datadist 0.0.1 llm_manager_python_api_demo 2.1rc1 llvmlite 0.43.0 lm-format-enforcer 0.10.12 loguru 0.7.2 lxml 5.3.0 Markdown 3.7 markdown-it-py 3.0.0 MarkupSafe 2.1.5 math-verify 0.5.2 matplotlib 3.9.2 mdtex2html 1.3.0 mdurl 0.1.2 mies_tokenizer 0.0.1 mindie_llm 2.1rc1 mindiebenchmark 2.1rc1 mindieclient 2.1rc1 mindiesd 2.1rc1 mindiesimulator 0.0.1 mindietorch 2.1rc1+torch2.1.0.abi0 mistral_common 1.8.3 ml_dtypes 0.5.1 mmengine-lite 0.10.7 model_wrapper 0.0.1 modelscope 1.28.0 mpmath 1.3.0 ms_swift 3.5.3 msgspec 0.19.0 msguard 0.0.7 msit 8.0.0 msit-llm 8.0.0 msmodelslim 7.0.0rc912 msobjdump 0.1.0 msprechecker 0.0.7 multidict 6.6.3 multiprocess 0.70.16 namex 0.1.0 narwhals 2.0.1 nest-asyncio 1.6.0 networkx 3.3 ninja 1.11.1.4 nltk 3.9.1 numba 0.60.0 numpy 1.26.4 om_adapter 0.0.1 onnx 1.18.0 op_compile_tool 0.1.0 op_gen 0.1 op_test_frame 0.1 opc_tool 0.1.0 openai 1.98.0 opencv-python-headless 4.11.0.86 openpyxl 3.1.5 opt_einsum 3.4.0 optree 0.16.0 orjson 3.11.1 oss2 2.19.1 outlines 0.1.11 outlines_core 0.1.26 packaging 24.1 pandas 1.5.3 partial-json-parser 0.2.1.1.post6 pathlib2 2.3.7.post1 peft 0.15.2 pillow 10.3.0 pip 23.3.1 platformdirs 4.3.8 plotly 6.2.0 portalocker 2.10.1 posix_ipc 1.2.0 prettytable 3.11.0 prometheus_client 0.22.1 prometheus-fastapi-instrumentator 7.1.0 propcache 0.3.2 protobuf 5.29.5 psutil 6.0.0 py-cpuinfo 9.0.0 pyarrow 17.0.0 pycountry 24.6.1 pycparser 2.22 pycryptodome 3.23.0 pydantic 2.9.2 pydantic_core 2.23.4 pydantic-extra-types 2.10.5 pydub 0.25.1 pyext 0.5 Pygments 2.19.2 pyparsing 3.1.4 python-dateutil 2.9.0.post0 python-Levenshtein 0.27.1 python-multipart 0.0.20 python-rapidjson 1.20 pytz 2024.2 PyYAML 6.0.2 pyzmq 26.4.0 qwen-vl-utils 0.0.11 rank-bm25 0.2.2 RapidFuzz 3.10.0 referencing 0.36.2 regex 2024.9.11 requests 2.32.3 retrying 1.4.1 rich 14.1.0 rouge 1.0.1 rouge-chinese 1.0.3 rouge-score 0.1.2 rpds-py 0.27.0 rpm 4.18.2 ruff 0.12.3 sacrebleu 2.4.3 safehttpx 0.1.6 safetensors 0.4.5 schedule_search 0.0.1 scikit-learn 1.5.0 scipy 1.14.1 seaborn 0.13.2 semantic-version 2.10.0 sentencepiece 0.2.0 setuptools 68.0.0 setuptools-scm 8.1.0 shellingham 1.5.4 show_kernel_debug_data 0.1.0 simplejson 3.20.1 six 1.16.0 sniffio 1.3.1 sortedcontainers 2.4.0 starlette 0.47.1 sympy 1.13.1 tabulate 0.9.0 te 0.4.0 tensorboard 2.19.0 tensorboard-data-server 0.7.2 tensorflow 2.19.0 tensorflow-io-gcs-filesystem 0.37.1 termcolor 2.4.0 text-generation 0.7.0 tf_keras 2.19.0 thefuzz 0.22.1 threadpoolctl 3.6.0 tiktoken 0.7.0 timeout-decorator 0.5.0 tokenizers 0.21.2 tomlkit 0.13.3 torch 2.5.1 torch_atb 0.0.1 torch-npu 2.5.1 torchvision 0.20.1 tornado 6.4.1 tqdm 4.66.5 transformers 4.49.0 transformers-stream-generator 0.0.5 tree-sitter 0.21.3 tree-sitter-languages 1.10.2 tritonclient 2.49.0 trl 0.19.1 typer 0.16.0 typing_extensions 4.12.2 tzdata 2024.2 urllib3 2.2.3 uvicorn 0.35.0 vllm 0.7.3+empty vllm 0.7.3+empty vllm-ascend 0.7.3.post1 watchdog 6.0.0 wcwidth 0.2.13 websockets 15.0.1 Werkzeug 3.1.3 wheel 0.44.0 wrapt 1.17.2 xxhash 3.5.0 yapf 0.43.0 yarl 1.20.1 zipp 3.23.0 zope.event 5.0 zope.interface 7.0.3 zstandard 0.23.0
config.json：
{ "Version": "1.0.0", "ServerConfig": { "ipAddress": "0.0.0.0", "managementIpAddress": "127.0.0.2", "port": 7860, "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": 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, 2, 3 ] ], "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": 25600, "maxInputTokenLen": 8192, "truncation": false, "ModelConfig": [ { "modelInstanceType": "Standard", "modelName": "qwen2_5_vl", "modelWeightPath": "/workspace/models/Qwen2.5-VL-7B-Instruct", "worldSize": 4, "cpuMemSize": 5, "npuMemSize": -1, "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": 10240, "prefillTimeMsPerReq": 150, "prefillPolicyType": 0, "decodeTimeMsPerReq": 50, "decodePolicyType": 0, "maxBatchSize": 300, "maxIterTimes": 512, "maxPreemptCount": 0, "supportSelectBatch": false, "maxQueueDelayMicroseconds": 5000 } } }
有没有大佬帮忙分析下
本帖最后由 匿名用户 于 2025/08/11 11:19:58 编辑
我要发帖子
点赞
收藏
回复
分享
举报
已解决 已解决
环境是华为昇腾910B算力卡 + openEuler 24.03 LTS环境，基础镜像是2.1.RC1-800I-A2-py311-openeuler24.03-lts，推理qwen2.5-vl报错：
包环境如下：
config.json：
{ "Version": "1.0.0", "ServerConfig": { "ipAddress": "0.0.0.0", "managementIpAddress": "127.0.0.2", "port": 7860, "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": 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, 2, 3 ] ], "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": 25600, "maxInputTokenLen": 8192, "truncation": false, "ModelConfig": [ { "modelInstanceType": "Standard", "modelName": "qwen2_5_vl", "modelWeightPath": "/workspace/models/Qwen2.5-VL-7B-Instruct", "worldSize": 4, "cpuMemSize": 5, "npuMemSize": -1, "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": 10240, "prefillTimeMsPerReq": 150, "prefillPolicyType": 0, "decodeTimeMsPerReq": 50, "decodePolicyType": 0, "maxBatchSize": 300, "maxIterTimes": 512, "maxPreemptCount": 0, "supportSelectBatch": false, "maxQueueDelayMicroseconds": 5000 } } }有没有大佬帮忙分析下