(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347] 
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347]        █     █     █▄   ▄█
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.29.0
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347]   █▄█▀ █     █     █     █  model   /root/.cache/huggingface/hub/models--bottlecapai--ThinkingCap-Qwen3.8-27B-NVFP4A4-AWQ/snapshots/f8fe157f207a13f977bc3d620ce10a3e9ba5ab11
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:347] 
(APIServer pid=1) INFO 09-24 04:19:17 [api_utils.py:286] non-default args: {'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_xml', 'host': '0.0.0.0', 'port': 39283, 'model': '/root/.cache/huggingface/hub/models--bottlecapai--ThinkingCap-Qwen3.8-27B-NVFP4A4-AWQ/snapshots/f8fe157f207a13f977bc3d620ce10a3e9ba5ab11', 'max_model_len': 131072, 'served_model_name': ['thinkingcap-awq-5090'], 'generation_config': 'vllm', 'attention_backend': 'TRITON_ATTN', 'reasoning_parser': 'qwen3', 'gpu_memory_utilization': 0.95, 'kv_cache_dtype': 'bfloat16', 'enable_prefix_caching': False, 'limit_mm_per_prompt': {'image': 2, 'video': 0}, 'mm_processor_kwargs': {'size': {'longest_edge': 1048576, 'shortest_edge': 65536}}, 'max_num_batched_tokens': 1024, 'max_num_seqs': 1}
(APIServer pid=1) INFO 09-24 04:19:17 [model.py:684] Resolved architecture: Qwen3_5ForConditionalGeneration
(APIServer pid=1) INFO 09-24 04:19:17 [model.py:2021] Using max model len 131072
(APIServer pid=1) INFO 09-24 04:19:24 [scheduler.py:277] Chunked prefill is enabled with max_num_batched_tokens=1024.
(APIServer pid=1) INFO 09-24 04:19:24 [kernel.py:369] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(EngineCore pid=116) INFO 09-24 04:19:41 [core.py:123] Initializing a V1 LLM engine (v0.29.0) with config: model='/root/.cache/huggingface/hub/models--bottlecapai--ThinkingCap-Qwen3.8-27B-NVFP4A4-AWQ/snapshots/f8fe157f207a13f977bc3d620ce10a3e9ba5ab11', speculative_config=None, tokenizer='/root/.cache/huggingface/hub/models--bottlecapai--ThinkingCap-Qwen3.8-27B-NVFP4A4-AWQ/snapshots/f8fe157f207a13f977bc3d620ce10a3e9ba5ab11', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=compressed-tensors, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=bfloat16, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, per_request_spec_decode_metrics='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, jit_monitor_mode='warn', jit_monitor_verbose=False), seed=0, served_model_name=thinkingcap-awq-5090, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'ir_enable_torch_wrap': True, 'splitting_ops': ['vllm::unified_attention_with_output', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::qwen4_exp_compute_ple_ngram_ids', 'vllm::qwen4_exp_ple_short_conv', 'vllm::qwen4_exp_qsa_with_output', 'vllm::linear_attention', 'vllm::qwen_gdn_attention_core', 'vllm::qwen_gdn_attention_core_fused_norm_packed', 'vllm::gdn_attention_core_xpu', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::deepseek_v4_attention', 'vllm::hpc_rope_norm_forward', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': [], 'compile_ranges_endpoints': [1024], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2], '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, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'enable_qk_norm_rope_fusion': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False, 'fuse_qk_norm_rope_kvcache': False}, 'max_cudagraph_capture_size': 2, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']), enable_flashinfer_autotune=True, enable_cutedsl_warmup=True, enable_jit_warmup=True, enable_bf16x3_router_gemm=False, moe_backend='auto', linear_backend='auto')
(EngineCore pid=116) INFO 09-24 04:19:42 [parallel_state.py:1775] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_7d635ae98e064d3bab1080333b6af046 backend=nccl
(EngineCore pid=116) INFO 09-24 04:19:42 [parallel_state.py:2119] 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, EPLB rank N/A
(EngineCore pid=116) INFO 09-24 04:19:42 [gpu_worker.py:429] Using V2 Model Runner
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374] EngineCore failed to start.
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374] Traceback (most recent call last):
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 1336, in run_engine_core
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     return func(*args, **kwargs)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 1093, in __init__
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     super().__init__(
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 134, in __init__
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     self.model_executor = executor_class(vllm_config)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     return func(*args, **kwargs)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/abstract.py", line 110, in __init__
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     self._init_executor()
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/uniproc_executor.py", line 69, in _init_executor
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     self.driver_worker.init_device()
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 355, in init_device
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     self.worker.init_device()  # type: ignore
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     return func(*args, **kwargs)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 440, in init_device
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     self.requested_memory = request_memory(init_snapshot, self.cache_config)
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/utils.py", line 526, in request_memory
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374]     raise ValueError(
(EngineCore pid=116) ERROR 09-24 04:19:43 [core.py:1374] ValueError: Free memory on device cuda:0 (30.2/31.82 GiB) on startup is less than desired GPU memory utilization (0.95, 30.23 GiB). Decrease GPU memory utilization or reduce GPU memory used by other processes.
(APIServer pid=1) INFO 09-24 04:19:44 [utils.py:620] [shutdown] Process manager: send sigterm to process EngineCore