INFO: Started server process [67062] INFO: Waiting for application startup. Loading model from /root/openbiollm-model via vLLM ... INFO 02-25 02:31:45 [model.py:541] Resolved architecture: LlamaForCausalLM INFO 02-25 02:31:45 [model.py:1561] Using max model len 2048 INFO 02-25 02:31:45 [scheduler.py:226] Chunked prefill is enabled with max_num_batched_tokens=2048. INFO 02-25 02:31:45 [vllm.py:624] Asynchronous scheduling is enabled. WARNING 02-25 02:31:45 [vllm.py:662] Enforce eager set, overriding optimization level to -O0 INFO 02-25 02:31:45 [vllm.py:762] Cudagraph is disabled under eager mode (EngineCore_DP0 pid=67100) INFO 02-25 02:31:46 [core.py:96] Initializing a V1 LLM engine (v0.15.1) with config: model='/root/openbiollm-model', speculative_config=None, tokenizer='/root/openbiollm-model', 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=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=/root/openbiollm-model, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': , 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': , 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': , 'evaluate_guards': False, 'assume_32_bit_indexing': True}, 'local_cache_dir': None, 'static_all_moe_layers': []} (EngineCore_DP0 pid=67100) INFO 02-25 02:31:48 [parallel_state.py:1212] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://65.109.75.18:36249 backend=nccl (EngineCore_DP0 pid=67100) INFO 02-25 02:31:48 [parallel_state.py:1423] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A (EngineCore_DP0 pid=67100) INFO 02-25 02:31:49 [gpu_model_runner.py:4033] Starting to load model /root/openbiollm-model... (EngineCore_DP0 pid=67100) INFO 02-25 02:31:50 [cuda.py:364] Using FLASH_ATTN attention backend out of potential backends: ('FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION') (EngineCore_DP0 pid=67100) Loading pt checkpoint shards: 0% Completed | 0/4 [00:00