2026-10-02T17:06:53.756748092Z (APIServer pid=1) INFO: 10.0.0.224:56244 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:53.853523505Z (APIServer pid=1) INFO: 10.0.0.224:57800 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:54.535625263Z (APIServer pid=1) INFO: 10.0.0.224:51734 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:06:54.564867700Z (APIServer pid=1) INFO: 10.0.0.224:56246 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:54.623824413Z (APIServer pid=1) INFO: 10.0.0.224:56250 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:54.632203564Z (APIServer pid=1) INFO: 10.0.0.224:56254 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:54.967331607Z (APIServer pid=1) INFO: 10.0.0.224:56258 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:55.505599059Z (APIServer pid=1) INFO: 10.0.0.224:51348 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:55.537199183Z (APIServer pid=1) INFO: 10.0.0.224:51734 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:06:55.564913045Z (APIServer pid=1) INFO: 10.0.0.224:51382 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:55.979097467Z (APIServer pid=1) INFO: 10.0.0.224:51386 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:56.535968361Z (APIServer pid=1) INFO: 10.0.0.224:51734 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:06:56.673230688Z (APIServer pid=1) INFO: 10.0.0.224:32934 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:56.903014169Z (APIServer pid=1) INFO: 10.0.0.224:51332 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:56.924254937Z (APIServer pid=1) INFO: 10.0.0.224:32900 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:57.537848317Z (APIServer pid=1) INFO: 10.0.0.224:51734 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:06:58.076413931Z (APIServer pid=1) INFO: 10.0.0.224:56138 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.226251064Z (APIServer pid=1) INFO: 10.0.0.224:56146 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.380400544Z (APIServer pid=1) INFO: 10.0.0.224:51362 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.438180307Z (APIServer pid=1) INFO: 10.0.0.224:56124 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.520200487Z (APIServer pid=1) INFO: 10.0.0.224:56108 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.531141892Z (APIServer pid=1) INFO: 10.0.0.224:56100 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:06:58.536533165Z (APIServer pid=1) INFO: 10.0.0.224:51734 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:06:58.540227436Z (APIServer pid=1) INFO: 10.0.0.224:52204 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:07:11.931965950Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] 2026-10-02T17:07:11.932028278Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] █ █ █▄ ▄█ 2026-10-02T17:07:11.932035581Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.29.0 2026-10-02T17:07:11.932040852Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] █▄█▀ █ █ █ █ model Qwen/Qwen2.5-7B-Instruct 2026-10-02T17:07:11.932046021Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀ 2026-10-02T17:07:11.932050710Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:347] 2026-10-02T17:07:11.939010683Z (APIServer pid=1) INFO 10-02 17:07:11 [api_utils.py:286] non-default args: {'model_tag': 'Qwen/Qwen2.5-7B-Instruct', 'host': '0.0.0.0', 'model': 'Qwen/Qwen2.5-7B-Instruct', 'revision': 'a09a35458c702b33eeacc393d103063234e8bc28', 'max_model_len': 1024, 'served_model_name': ['Qwen/Qwen2.5-7B-Instruct'], 'kv_cache_memory_bytes': 17179869184, 'enable_prefix_caching': False, 'cudagraph_metrics': True, 'max_num_seqs': 256, 'optimization_level': '2'} 2026-10-02T17:07:12.129462178Z (APIServer pid=1) INFO 10-02 17:07:12 [model.py:684] Resolved architecture: Qwen2ForCausalLM 2026-10-02T17:07:12.129819243Z (APIServer pid=1) INFO 10-02 17:07:12 [model.py:2021] Using max model len 1024 2026-10-02T17:07:12.133251578Z (APIServer pid=1) INFO 10-02 17:07:12 [kernel.py:369] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']) 2026-10-02T17:07:22.896842688Z (EngineCore pid=72) INFO 10-02 17:07:22 [core.py:123] Initializing a V1 LLM engine (v0.29.0) with config: model='Qwen/Qwen2.5-7B-Instruct', speculative_config=None, tokenizer='Qwen/Qwen2.5-7B-Instruct', skip_tokenizer_init=False, tokenizer_mode=auto, revision=a09a35458c702b33eeacc393d103063234e8bc28, tokenizer_revision=a09a35458c702b33eeacc393d103063234e8bc28, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=1024, 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=None, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', 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, per_request_spec_decode_metrics='none', kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=True, 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=Qwen/Qwen2.5-7B-Instruct, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': , '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': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': , 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], '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': 512, 'dynamic_shapes_config': {'type': , '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') 2026-10-02T17:07:25.233767376Z (EngineCore pid=72) :1297: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead. 2026-10-02T17:07:25.233952094Z (EngineCore pid=72) :1297: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead. 2026-10-02T17:07:25.864263152Z (EngineCore pid=72) INFO 10-02 17:07:25 [parallel_state.py:1775] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_0ea69f3891a1494ebb76409235977df3 backend=nccl 2026-10-02T17:07:25.872824226Z (EngineCore pid=72) INFO 10-02 17:07:25 [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 2026-10-02T17:07:25.872835787Z (EngineCore pid=72) INFO 10-02 17:07:25 [gpu_worker.py:429] Using V2 Model Runner 2026-10-02T17:07:26.778799343Z (EngineCore pid=72) INFO 10-02 17:07:26 [model_runner.py:382] Loading model from scratch... 2026-10-02T17:07:26.923418599Z (EngineCore pid=72) INFO 10-02 17:07:26 [cuda.py:492] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. 2026-10-02T17:07:26.923743402Z (EngineCore pid=72) INFO 10-02 17:07:26 [flash_attn.py:897] Using FlashAttention version 2 2026-10-02T17:07:27.304792437Z (EngineCore pid=72) INFO 10-02 17:07:27 [weight_utils.py:863] Filesystem type for checkpoints: EXT4. Checkpoint size: 14.19 GiB. Available RAM: 52.02 GiB. 2026-10-02T17:07:27.305003345Z (EngineCore pid=72) INFO 10-02 17:07:27 [weight_utils.py:886] Auto-prefetch is disabled because the filesystem (EXT4) is not a recognized network FS (NFS/Lustre). If you want to force prefetching, start vLLM with --safetensors-load-strategy=prefetch. 2026-10-02T17:07:27.305344298Z (EngineCore pid=72) Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00