同主机上部署有deepseek-32b模型，运行正常

mis-tei版本  7.2.RC1-300I-Duo-aarch64

错误日志：

Model '/home/HwHiAiUser/model/Qwen3-Embedding-0.6B' exists. run on device 0 Starting TEI service on 221.195.12.206:9901... 2025-12-02T15:51:40.036627Z INFO text_embeddings_router: router/src/main.rs:189: Args { model_id: "Qwe**-*********-0.6B", revision: None, tokenization_workers: None, dtype: None, pooling: None, max_concurrent_requests: 64, max_batch_tokens: 16384, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: false, default_prompt_name: None, default_prompt: None, hf_api_token: None, hf_token: None, hostname: "221.195.12.206", port: 9901, uds_path: "/tmp/text-embeddings-inference-server", huggingface_hub_cache: None, payload_limit: 2000000, api_key: None, json_output: false, disable_spans: false, otlp_endpoint: None, otlp_service_name: "text-embeddings-inference.server", prometheus_port: 9900, cors_allow_origin: None } 2025-12-02T15:51:41.559223Z WARN text_embeddings_router: router/src/lib.rs:208: Could not find a Sentence Transformers config 2025-12-02T15:51:41.559321Z INFO text_embeddings_router: router/src/lib.rs:212: Maximum number of tokens per request: 32768 2025-12-02T15:51:41.559963Z INFO text_embeddings_core::tokenization: core/src/tokenization.rs:38: Starting 96 tokenization workers 2025-12-02T15:51:55.605829Z INFO text_embeddings_router: router/src/lib.rs:254: Starting model backend 2025-12-02T15:51:55.614568Z INFO text_embeddings_backend_python::management: backends/python/src/management.rs:68: Starting Python backend 2025-12-02T15:51:58.025487Z ERROR text_embeddings_backend: backends/src/lib.rs:428: Could not start Python backend: Could not start backend: Python Backend process was signaled to shutdown with signal 9 Error: Could not create backend Caused by: Could not start backend: Could not start a suitable backend