{ "container": "vllm", "before": { "running": true, "pid": 3174, "id": "8fa002d66b940e87ba57ccab24dbcf13d4e227905d8e016d2ef905005bd277d4", "started_at": "2026-10-02T16:05:25.701058951Z", "finished_at": "0001-01-01T00:00:00Z", "restart_count": 0, "restart_policy": "on-failure" }, "after": { "running": true, "pid": 4451, "id": "8fa002d66b940e87ba57ccab24dbcf13d4e227905d8e016d2ef905005bd277d4", "started_at": "2026-10-02T16:08:14.215990487Z", "finished_at": "2026-10-02T16:08:14.201078322Z", "restart_count": 1, "restart_policy": "on-failure" }, "offset_before": { "offset_ns": 8443194, "bound_ns": 7497245, "samples": 5, "at": "2026-10-02T16:08:08.004225121Z" }, "offset_after": { "offset_ns": 9070011, "bound_ns": 7964125, "samples": 5, "at": "2026-10-02T16:08:55.697399105Z" }, "signal_zero": [ { "pid": 3174, "signal": 0, "sent_at": "2026-10-02T16:08:08.004241529Z", "returned_at": "2026-10-02T16:08:08.048488501Z", "remote_before_ns": 1790957288046558637, "remote_after_ns": 1790957288048479317 }, { "pid": 3174, "signal": 0, "sent_at": "2026-10-02T16:08:08.048515391Z", "returned_at": "2026-10-02T16:08:08.09170707Z", "remote_before_ns": 1790957288090415143, "remote_after_ns": 1790957288091762992 }, { "pid": 3174, "signal": 0, "sent_at": "2026-10-02T16:08:08.091736171Z", "returned_at": "2026-10-02T16:08:08.132667579Z", "remote_before_ns": 1790957288131441283, "remote_after_ns": 1790957288132609865 }, { "pid": 3174, "signal": 0, "sent_at": "2026-10-02T16:08:08.132679799Z", "returned_at": "2026-10-02T16:08:08.176916277Z", "remote_before_ns": 1790957288175560493, "remote_after_ns": 1790957288176772337 }, { "pid": 3174, "signal": 0, "sent_at": "2026-10-02T16:08:08.176924775Z", "returned_at": "2026-10-02T16:08:08.222234497Z", "remote_before_ns": 1790957288221122133, "remote_after_ns": 1790957288222033070 } ], "signal_zero_round_trip_ms": [ 44.246, 43.191, 40.931, 44.236, 45.309 ], "signal_zero_bracket_ms": [ 1.92068, 1.347849, 1.168582, 1.211844, 0.910937 ], "orchestration": { "armed_at": "2026-10-02T16:08:08.222256636Z", "planned_fire_at": "2026-10-02T16:08:13.222246767Z", "planned_expiry_at": "2026-10-02T16:08:23.222246767Z", "observed_fire_at": "2026-10-02T16:08:13.261594593Z", "observed_expiry_at": "2026-10-02T16:08:13.261594593Z" }, "kill": { "pid": 3174, "signal": 9, "sent_at": "2026-10-02T16:08:13.223249679Z", "returned_at": "2026-10-02T16:08:13.271237595Z", "remote_before_ns": 1790957293269189373, "remote_after_ns": 1790957293270886201 }, "fire_error_ms": 39.347, "fire_uncertainty_ns": 9439356, "restart_count_advanced": 1, "events": [ { "action": "die", "at": "2026-10-02T16:08:14.203768583Z" }, { "action": "start", "at": "2026-10-02T16:08:14.476245614Z" } ], "die_to_start_s": 0.272477031, "health_calibration_started_at": "2026-10-02T16:08:13.341448143Z", "health_calibration_lag_after_fire_s": 0.079853436, "health_calibration": { "health_ready_after_s": 42.159790706, "inference_ready_after_s": 42.212637702, "gap_s": 0.052846995999999535, "health_ok": true, "inference_ok": true, "note": "health-ready and serve-ready coincide within 0.5s on this version" }, "health_ready_after_fire_s": 42.239644142, "inference_ready_after_fire_s": 42.292491138, "boundaries": { "matches": { "banner": { "key": "banner", "line": 4, "at": "2026-10-02T16:08:25.383087855Z", "stamp": "docker", "resolution_ns": 1, "text": "2026-10-02T16:08:25.383087855Z (APIServer pid=1) INFO 10-02 16:08:25 [api_utils.py:347] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.29.0" }, "engine_init": { "key": "engine_init", "line": 12, "at": "2026-10-02T16:08:35.2721518Z", "stamp": "docker", "resolution_ns": 1, "text": "2026-10-02T16:08:35.272151800Z (EngineCore pid=72) INFO 10-02 16:08:35 [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': \u003cCompilationMode.VLLM_COMPILE: 3\u003e, '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': \u003cCUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)\u003e, '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': \u003cDynamicShapesType.BACKED: 'backed'\u003e, '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')" }, "engine_ready": { "key": "engine_ready", "line": 47, "at": "2026-10-02T16:08:53.43774163Z", "stamp": "docker", "resolution_ns": 1, "figures": { "init_engine_compilation_s": 0.17, "init_engine_s": 10.18 }, "text": "2026-10-02T16:08:53.437741630Z (EngineCore pid=72) INFO 10-02 16:08:53 [core.py:361] init engine (profile, create kv cache, warmup model) took 10.18 s (compilation: 0.17 s)" }, "graph_capture": { "key": "graph_capture", "line": 44, "at": "2026-10-02T16:08:49.925018808Z", "stamp": "docker", "resolution_ns": 1, "figures": { "graph_capture_gib": 0.52, "graph_capture_s": 5 }, "text": "2026-10-02T16:08:49.925018808Z (EngineCore pid=72) INFO 10-02 16:08:49 [model_runner.py:960] Graph capturing finished in 5 secs, took 0.52 GiB" }, "model_load_start": { "key": "model_load_start", "line": 18, "at": "2026-10-02T16:08:39.276849086Z", "stamp": "docker", "resolution_ns": 1, "text": "2026-10-02T16:08:39.276849086Z (EngineCore pid=72) INFO 10-02 16:08:39 [model_runner.py:382] Loading model from scratch..." }, "model_loaded": { "key": "model_loaded", "line": 31, "at": "2026-10-02T16:08:43.249011218Z", "stamp": "docker", "resolution_ns": 1, "figures": { "model_loaded_gib": 14.29, "model_loaded_s": 4.288191 }, "text": "2026-10-02T16:08:43.249011218Z (EngineCore pid=72) INFO 10-02 16:08:43 [model_runner.py:404] Model loading took 14.29 GiB memory and 4.288191 seconds" }, "server_start": { "key": "server_start", "line": 54, "at": "2026-10-02T16:08:54.877365997Z", "stamp": "docker", "resolution_ns": 1, "text": "2026-10-02T16:08:54.877365997Z (APIServer pid=1) INFO 10-02 16:08:54 [entry.py:139] Starting vLLM server on http://0.0.0.0:8000" }, "startup_complete": { "key": "startup_complete", "line": 109, "at": "2026-10-02T16:08:55.209821682Z", "stamp": "docker", "resolution_ns": 1, "text": "2026-10-02T16:08:55.209821682Z (APIServer pid=1) INFO: Application startup complete." }, "torch_compile": { "key": "torch_compile", "line": 36, "at": "2026-10-02T16:08:43.963258631Z", "stamp": "docker", "resolution_ns": 1, "figures": { "torch_compile_s": 0.17 }, "text": "2026-10-02T16:08:43.963258631Z (EngineCore pid=72) INFO 10-02 16:08:43 [monitor.py:53] torch.compile took 0.17 s in total" }, "weights_loaded": { "key": "weights_loaded", "line": 30, "at": "2026-10-02T16:08:42.578441936Z", "stamp": "docker", "resolution_ns": 1, "figures": { "weights_loaded_s": 2.76 }, "text": "2026-10-02T16:08:42.578441936Z (EngineCore pid=72) INFO 10-02 16:08:42 [default_loader.py:430] Loading weights took 2.76 seconds" } }, "lines": 111 }, "log_path": "results/dry-kill/dry-kill-server.log", "log_bytes": 23700 }