$ ilab model serve
INFO 2025-04-29 10:21:07,007 instructlab.model.serve_backend:79: Setting backend_type in the serve config to vllm
INFO 2025-04-29 10:21:07,019 instructlab.model.serve_backend:85: Using model '/var/home/azureuser/.cache/instructlab/models/granite-3.1-8b-lab-v1' with -1 gpu-layers and 4096 max context size.
INFO 2025-04-29 10:21:14,029 instructlab.model.serve_backend:127: '--gpus' flag used alongside '--tensor-parallel-size' in the vllm_args section of the config file. Using value of the --gpus flag.
INFO 2025-04-29 10:21:14,205 instructlab.model.backends.vllm:332: vLLM starting up on pid 6 at http://127.0.0.1:8000/v1
INFO 04-29 10:23:35 [__init__.py:243] No platform detected, vLLM is running on UnspecifiedPlatform
INFO 04-29 10:23:43 [api_server.py:1034] vLLM API server version 0.8.4
INFO 04-29 10:23:43 [api_server.py:1035] args: Namespace(host='127.0.0.1', port=8000, uvicorn_log_level='info', disable_uvicorn_access_log=False, allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template='/tmp/tmpvkgs3_o9', chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='/var/home/azureuser/.cache/instructlab/models/granite-3.1-8b-lab-v1', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, load_format='auto', download_dir=None, model_loader_extra_config=None, use_tqdm_on_load=True, config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=None, guided_decoding_backend='auto', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend='mp', pipeline_parallel_size=1, tensor_parallel_size=8, data_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, disable_custom_all_reduce=False, block_size=None, enable_prefix_caching=None, prefix_caching_hash_algo='builtin', disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=None, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_token=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['/var/home/azureuser/.cache/instructlab/models/granite-3.1-8b-lab-v1', 'granite-3.1-8b-lab-v1', 'models/granite-3.1-8b-lab-v1', 'models/granite-3.1-8b-starter-v1'], qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, additional_config=None, enable_reasoning=False, reasoning_parser=None, disable_cascade_attn=False, disable_chunked_mm_input=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False)
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 1121, in <module>
    uvloop.run(run_server(args))
  File "/opt/app-root/lib64/python3.11/site-packages/uvloop/__init__.py", line 105, in run
    return runner.run(wrapper())
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib64/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/opt/app-root/lib64/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 1069, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/usr/lib64/python3.11/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 146, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/usr/lib64/python3.11/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 166, in build_async_engine_client_from_engine_args
    vllm_config = engine_args.create_engine_config(usage_context=usage_context)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/engine/arg_utils.py", line 1153, in create_engine_config
    device_config = DeviceConfig(device=self.device)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/app-root/lib64/python3.11/site-packages/vllm/config.py", line 2007, in __init__
    raise RuntimeError(
RuntimeError: Failed to infer device type, please set the environment variable `VLLM_LOGGING_LEVEL=DEBUG` to turn on verbose logging to help debug the issue.