jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py", line 1010, in hf_hub_download\n
jrh9pgmv08jt16[info]    return fn(*args, **kwargs)\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn\n
jrh9pgmv08jt16[info]    hf_hub_download(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py", line 479, in cached_files\n
jrh9pgmv08jt16[info]    raise e\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py", line 567, in cached_files\n
jrh9pgmv08jt16[info]    file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs)\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py", line 321, in cached_file\n
jrh9pgmv08jt16[info]    resolved_vocab_files[file_id] = cached_file(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 2032, in from_pretrained\n
jrh9pgmv08jt16[info]    return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/tokenization_auto.py", line 1116, in from_pretrained\n
jrh9pgmv08jt16[info]    tokenizer = AutoTokenizer.from_pretrained(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/transformers_utils/tokenizer.py", line 238, in get_tokenizer\n
jrh9pgmv08jt16[info]    self.tokenizer = get_tokenizer(self.tokenizer_id, **tokenizer_config)\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/transformers_utils/tokenizer_group.py", line 24, in __init__\n
jrh9pgmv08jt16[info]    return TokenizerGroup(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/transformers_utils/tokenizer_group.py", line 111, in init_tokenizer_from_configs\n
jrh9pgmv08jt16[info]    self.tokenizer = init_tokenizer_from_configs(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/v1/engine/async_llm.py", line 100, in __init__\n
jrh9pgmv08jt16[info]    return cls(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/v1/engine/async_llm.py", line 163, in from_vllm_config\n
jrh9pgmv08jt16[info]    return async_engine_cls.from_vllm_config(\n
jrh9pgmv08jt16[info]  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 653, in from_engine_args\n
jrh9pgmv08jt16[info]    engine = AsyncLLMEngine.from_engine_args(self.engine_args)\n
jrh9pgmv08jt16[info]  File "/src/engine.py", line 165, in _initialize_llm\n
jrh9pgmv08jt16[info]    raise e\n
jrh9pgmv08jt16[info]  File "/src/engine.py", line 171, in _initialize_llm\n
jrh9pgmv08jt16[info]    self.llm = self._initialize_llm() if engine is None else engine.llm\n
jrh9pgmv08jt16[info]  File "/src/engine.py", line 30, in __init__\n
jrh9pgmv08jt16[info]    vllm_engine = vLLMEngine()\n
jrh9pgmv08jt16[info]  File "/src/handler.py", line 6, in <module>\n
jrh9pgmv08jt16[info]Traceback (most recent call last):\n
jrh9pgmv08jt16[info]engine.py           :170  2025-10-01 13:02:12,387 Error initializing vLLM engine: [Errno 30] Read-only file system: '/runpod-volume/huggingface-cache/hub/models--Sunbird--Sunflower-14B/blobs/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4.incomplete'\n
jrh9pgmv08jt16[info]INFO 10-01 13:02:11 [config.py:2434] Chunked prefill is enabled with max_num_batched_tokens=2048.\n
jrh9pgmv08jt16[info]INFO 10-01 13:02:11 [config.py:1604] Using max model len 2048\n