runtime error

Exit code: 1. Reason: v llama_server: loading model 1.25.748.822 I srv load_model: loading model '/home/user/hf/hub/models--unsloth--Qwen3.5-4B-GGUF/snapshots/e87f176479d0855a907a41277aca2f8ee7a09523/Qwen3.5-4B-Q4_K_M.gguf' 1.25.748.860 I common_init_result: fitting params to device memory ... 1.25.748.867 I common_init_result: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on) 1.26.470.235 I common_params_fit_impl: projected to use 1556 MiB of host memory vs. 126760 MiB of total host memory 1.28.655.277 W llama_context: n_ctx_seq (4096) < n_ctx_train (262144) -- the full capacity of the model will not be utilized 1.28.763.941 I common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) 1.29.301.516 I srv load_model: initializing slots, n_slots = 1 1.29.985.320 W srv load_model: speculative decoding will use checkpoints 1.29.985.337 W common_speculative_init: no implementations specified for speculative decoding 1.29.985.338 I slot load_model: id 0 | task -1 | new slot, n_ctx = 4096 1.29.985.441 I srv load_model: prompt cache is disabled - use `--cache-ram N` to enable it 1.29.985.447 I srv load_model: for more info see https://github.com/ggml-org/llama.cpp/pull/16391 1.29.985.449 I srv load_model: context checkpoints enabled, max = 32, min spacing = 256 1.29.985.473 W srv init: --cache-idle-slots requires --cache-ram, disabling 1.30.008.071 I init: chat template, example_format: '<|im_start|>system You are a helpful assistant<|im_end|> <|im_start|>user Hello<|im_end|> <|im_start|>assistant Hi there<|im_end|> <|im_start|>user How are you?<|im_end|> <|im_start|>assistant <think> </think> ' 1.30.027.692 I srv init: init: chat template, thinking = 0 1.30.027.746 I srv llama_server: model loaded 1.30.027.755 I srv llama_server: server is listening on http://127.0.0.1:8082 1.30.027.763 I srv update_slots: all slots are idle FATAL: llama-server on :8081 never became healthy

Container logs: