INFO 11-15 19:43:34 [__init__.py:216] Automatically detected platform cpu. Initializing vLLM engine... INFO 11-15 19:43:35 [utils.py:233] non-default args: {'dtype': 'bfloat16', 'max_model_len': 2048, 'gpu_memory_utilization': 0.3, 'disable_log_stats': True, 'model': 'Qwen/Qwen2.5-1.5B-Instruct'} INFO 11-15 19:43:38 [model.py:547] Resolved architecture: Qwen2ForCausalLM `torch_dtype` is deprecated! Use `dtype` instead! INFO 11-15 19:43:38 [model.py:1510] Using max model len 2048 WARNING 11-15 19:43:38 [cpu.py:117] Environment variable VLLM_CPU_KVCACHE_SPACE (GiB) for CPU backend is not set, using 4 by default. INFO 11-15 19:43:38 [arg_utils.py:1166] Chunked prefill is not supported for ARM and POWER and S390X CPUs; disabling it for V1 backend. INFO 11-15 19:43:41 [__init__.py:216] Automatically detected platform cpu. (EngineCore_DP0 pid=70077) INFO 11-15 19:43:42 [core.py:644] Waiting for init message from front-end. (EngineCore_DP0 pid=70077) INFO 11-15 19:43:42 [core.py:77] Initializing a V1 LLM engine (v0.11.0) with config: model='Qwen/Qwen2.5-1.5B-Instruct', speculative_config=None, tokenizer='Qwen/Qwen2.5-1.5B-Instruct', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=2048, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cpu, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=Qwen/Qwen2.5-1.5B-Instruct, enable_prefix_caching=True, chunked_prefill_enabled=False, pooler_config=None, compilation_config={"level":2,"debug_dump_path":"","cache_dir":"","backend":"inductor","custom_ops":["none"],"splitting_ops":null,"use_inductor":true,"compile_sizes":null,"inductor_compile_config":{"enable_auto_functionalized_v2":false,"dce":true,"size_asserts":false,"nan_asserts":false,"epilogue_fusion":true},"inductor_passes":{},"cudagraph_mode":0,"use_cudagraph":true,"cudagraph_num_of_warmups":0,"cudagraph_capture_sizes":[],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"use_inductor_graph_partition":false,"pass_config":{},"max_capture_size":null,"local_cache_dir":null} (EngineCore_DP0 pid=70077) INFO 11-15 19:43:42 [importing.py:63] Triton not installed or not compatible; certain GPU-related functions will not be available. (EngineCore_DP0 pid=70077) WARNING 11-15 19:43:42 [cpu.py:316] Pin memory is not supported on CPU. (EngineCore_DP0 pid=70077) INFO 11-15 19:43:43 [cpu_worker.py:66] Warning: NUMA is not enabled in this build. `init_cpu_threads_env` has no effect to setup thread affinity. (EngineCore_DP0 pid=70077) INFO 11-15 19:43:43 [parallel_state.py:1208] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0 (EngineCore_DP0 pid=70077) INFO 11-15 19:43:43 [cpu_model_runner.py:106] Starting to load model Qwen/Qwen2.5-1.5B-Instruct... (EngineCore_DP0 pid=70077) INFO 11-15 19:43:43 [cpu.py:104] Using Torch SDPA backend. (EngineCore_DP0 pid=70077) INFO 11-15 19:43:44 [weight_utils.py:392] Using model weights format ['*.safetensors'] (EngineCore_DP0 pid=70077) INFO 11-15 19:43:44 [weight_utils.py:450] No model.safetensors.index.json found in remote. Loading safetensors checkpoint shards: 0% Completed | 0/1 [00:00