runtime error

Exit code: 1. Reason: graph nodes = 1267 sched_reserve: graph splits = 1 sched_reserve: reserve took 62.64 ms, sched copies = 1 common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) srv load_model: initializing slots, n_slots = 1 no implementations specified for speculative decoding slot load_model: id 0 | task -1 | speculative decoding context not initialized slot load_model: id 0 | task -1 | new slot, n_ctx = 8192 srv load_model: prompt cache is disabled - use `--cache-ram N` to enable it srv load_model: for more info see https://github.com/ggml-org/llama.cpp/pull/16391 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 ' srv init: init: chat template, thinking = 0 main: model loaded main: server is listening on http://127.0.0.1:8080 main: starting the main loop... srv update_slots: all slots are idle [*] Server is ready! /app/app.py:122: UserWarning: The parameters have been moved from the Blocks constructor to the launch() method in Gradio 6.0: theme. Please pass these parameters to launch() instead. with gr.Blocks(theme="soft") as demo: * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ (experimental, to disable set `ssr_mode=False` in `launch()`) Traceback (most recent call last): File "/app/app.py", line 135, in <module> demo.launch(server_name="0.0.0.0", server_port=7860) ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/gradio/blocks.py", line 2812, in launch raise ValueError( "When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost." ) ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

Container logs: