{
  "row": 29,
  "utc": "2026-11-08T23:16:50.921113+00:00",
  "image": "sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568",
  "container": "9739e25ce75a4a0503e8fcf93898d09ad4442db529640456593e803bdad84a75",
  "runner_exit": 0,
  "manifest_sha256": "1d2c3350fafbf79cf6d1aca4a68e17a670c7f2e384ce7589e2d7f8bce876d262",
  "verified_regular_files": 173,
  "closure": {
    "Status": "exited",
    "Running": false,
    "Paused": false,
    "Restarting": false,
    "OOMKilled": false,
    "Dead": false,
    "Pid": 0,
    "ExitCode": 137,
    "Error": "",
    "StartedAt": "2026-11-08T22:58:14.831580175Z",
    "FinishedAt": "2026-11-08T23:16:33.728315227Z"
  },
  "restart_count": 0,
  "complete": true,
  "strict_pass": true,
  "limits": [
    "One fresh measurement per distinct runtime variant; grouped historical rows are not independent new samples.",
    "Historical published measurements remain separate from this fresh run.",
    "Installed source and mapped native identities establish admitted runtime, not a dynamic per-kernel invocation trace.",
    "Fresh root-SSD caches and the current host state differ from the historical runs.",
    "Physical VRAM is sampled, not a continuous peak; logged allocation budgets are separate from tensor-byte totals."
  ],
  "runtime-ready": {
    "sha256": "a34a256dfe030fc684afaa516c63086200d1ca32f8241ae5bbda940b05838b30",
    "installed_files": 43,
    "CPU_probe_contract_sha256": "6c3b0ccf1504dbe528abede52323a253b94cabd6366cbff2dbf83830c5dc302c",
    "actual_worker_PIDs_by_TP_rank": {
      "0": 327,
      "1": 328,
      "2": 329,
      "3": 330,
      "4": 331,
      "5": 332,
      "6": 333,
      "7": 334
    }
  },
  "runtime-after-ladder": {
    "sha256": "a99f04dce2b7fc0ea46570688362e040d2f620e2c0ac6284217dbff13fa495fa",
    "installed_files": 43,
    "CPU_probe_contract_sha256": "6c3b0ccf1504dbe528abede52323a253b94cabd6366cbff2dbf83830c5dc302c",
    "actual_worker_PIDs_by_TP_rank": {
      "0": 327,
      "1": 328,
      "2": 329,
      "3": 330,
      "4": 331,
      "5": 332,
      "6": 333,
      "7": 334
    }
  },
  "physical_memory": {
    "scope": "Physical device VRAM sampled every two seconds; may include allocations outside the test container. Sampled maximum is not an exact peak and not logical tensor bytes.",
    "samples": 517,
    "first_utc": "2026-11-08T22:58:14.994377+00:00",
    "last_utc": "2026-11-08T23:15:30.788448+00:00",
    "devices": [
      {
        "render": 128,
        "pci": "0000:06:00.0",
        "sampled_max_vram_bytes": 33791266816,
        "minimum_vram_bytes": 85454848
      },
      {
        "render": 129,
        "pci": "0000:09:00.0",
        "sampled_max_vram_bytes": 33666322432,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 130,
        "pci": "0000:45:00.0",
        "sampled_max_vram_bytes": 33716637696,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 131,
        "pci": "0000:48:00.0",
        "sampled_max_vram_bytes": 33666342912,
        "minimum_vram_bytes": 10862592
      },
      {
        "render": 132,
        "pci": "0000:89:00.0",
        "sampled_max_vram_bytes": 33716674560,
        "minimum_vram_bytes": 10862592
      },
      {
        "render": 133,
        "pci": "0000:8c:00.0",
        "sampled_max_vram_bytes": 33666342912,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 134,
        "pci": "0000:c5:00.0",
        "sampled_max_vram_bytes": 33716662272,
        "minimum_vram_bytes": 10854400
      },
      {
        "render": 135,
        "pci": "0000:c8:00.0",
        "sampled_max_vram_bytes": 33666334720,
        "minimum_vram_bytes": 10862592
      }
    ]
  },
  "runtime_configuration_source": {
    "container_inspect_sha256": "6c62a653bbea187610b1c6bff7936dfe16fb3cf62e2b67eb175e1823acefd6c5",
    "preflight_sha256": "d3a0cc16966e67c548b6f52061a89a323264b77cb434b0d4a89382f03e3e0919",
    "docker_run_sha256": "0eb3bb0bf19bd4960d8edb4c06191b172f4dbd377654320735a3a42ced61888a",
    "effective_engine_log_lines": [
      {
        "line": 8,
        "text": "2026-11-08T22:58:35.749740919Z (APIServer pid=146) INFO 11-08 22:58:35 [utils.py:228] non-default args: {'model_tag': '/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_coder', 'host': '0.0.0.0', 'port': 8078, 'model': '/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', 'trust_remote_code': True, 'dtype': 'half', 'max_model_len': 131072, 'served_model_name': ['Qwen3.6-27B-HF-CausalLM'], 'hf_overrides': {'architectures': ['Qwen3_5ForCausalLM']}, 'generation_config': 'vllm', 'reasoning_parser': 'qwen3', 'tensor_parallel_size': 8, 'gpu_memory_utilization': 0.95, 'enable_prefix_caching': False, 'language_model_only': True, 'max_num_batched_tokens': 4, 'max_num_seqs': 2, 'async_scheduling': True, 'optimization_level': '3'}"
      },
      {
        "line": 49,
        "text": "2026-11-08T22:58:56.339985059Z (APIServer pid=146) INFO 11-08 22:58:56 [model.py:1562] Using max model len 131072"
      },
      {
        "line": 57,
        "text": "2026-11-08T22:59:19.622039063Z (EngineCore_DP0 pid=273) INFO 11-08 22:59:19 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', speculative_config=None, tokenizer='/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=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='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, 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=Qwen3.6-27B-HF-CausalLM, 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': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], '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, 4], '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, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, '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': []}"
      }
    ]
  },
  "prepared_plan": {
    "row": 29,
    "profile": "hf-dense27b-tp8",
    "container_name": "historical-row29-4c3b6876ba-reproduction",
    "root": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29",
    "models_root": "/usr/share/ollama/localaiservers-repro-models",
    "image": "sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568",
    "docker_argv": [
      "docker",
      "run",
      "-d",
      "--name",
      "historical-row29-4c3b6876ba-reproduction",
      "--network",
      "host",
      "--ipc",
      "host",
      "--device",
      "/dev/kfd",
      "--device",
      "/dev/dri",
      "--group-add",
      "video",
      "--cap-add",
      "SYS_PTRACE",
      "--cap-add",
      "IPC_LOCK",
      "--security-opt",
      "seccomp=unconfined",
      "--security-opt",
      "label=disable",
      "--ulimit",
      "memlock=-1:-1",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/hf,dst=/root/.cache/huggingface",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/launch,dst=/runwork",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/vllm,dst=/root/.cache/vllm",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/triton,dst=/root/.triton",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/inductor,dst=/tmp/torchinductor_root",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/overlay,dst=/opt/vllm_patch_bundle,readonly",
      "--mount",
      "type=bind,src=/usr/share/ollama/localaiservers-repro-models/qwen36-dense,dst=/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9,readonly",
      "-e",
      "HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
      "-e",
      "LD_LIBRARY_PATH=/opt/gfx906:/rccl-overlay/install/lib:/usr/local/lib:/opt/rocm/lib:/opt/venv/lib/python3.12/site-packages/torch/lib",
      "-e",
      "VLLM_PATCH_BUNDLE=/opt/vllm_patch_bundle",
      "-e",
      "HF_HUB_OFFLINE=1",
      "--entrypoint",
      "/runwork/container_entrypoint.sh",
      "sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568"
    ],
    "docker_run": "docker \\\n  run \\\n  -d \\\n  --name \\\n  historical-row29-4c3b6876ba-reproduction \\\n  --network \\\n  host \\\n  --ipc \\\n  host \\\n  --device \\\n  /dev/kfd \\\n  --device \\\n  /dev/dri \\\n  --group-add \\\n  video \\\n  --cap-add \\\n  SYS_PTRACE \\\n  --cap-add \\\n  IPC_LOCK \\\n  --security-opt \\\n  seccomp=unconfined \\\n  --security-opt \\\n  label=disable \\\n  --ulimit \\\n  memlock=-1:-1 \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/hf,dst=/root/.cache/huggingface \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/launch,dst=/runwork \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/vllm,dst=/root/.cache/vllm \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/triton,dst=/root/.triton \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/inductor,dst=/tmp/torchinductor_root \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/overlay,dst=/opt/vllm_patch_bundle,readonly \\\n  --mount \\\n  type=bind,src=/usr/share/ollama/localaiservers-repro-models/qwen36-dense,dst=/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9,readonly \\\n  -e \\\n  HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \\\n  -e \\\n  LD_LIBRARY_PATH=/opt/gfx906:/rccl-overlay/install/lib:/usr/local/lib:/opt/rocm/lib:/opt/venv/lib/python3.12/site-packages/torch/lib \\\n  -e \\\n  VLLM_PATCH_BUNDLE=/opt/vllm_patch_bundle \\\n  -e \\\n  HF_HUB_OFFLINE=1 \\\n  --entrypoint \\\n  /runwork/container_entrypoint.sh \\\n  sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568",
    "required_models": [
      "qwen36-dense"
    ],
    "mounts": [
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/hf",
        "destination": "/root/.cache/huggingface",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/launch",
        "destination": "/runwork",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/vllm",
        "destination": "/root/.cache/vllm",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/triton",
        "destination": "/root/.triton",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/cache/inductor",
        "destination": "/tmp/torchinductor_root",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-29/overlay",
        "destination": "/opt/vllm_patch_bundle",
        "read_only": true
      },
      {
        "source": "/usr/share/ollama/localaiservers-repro-models/qwen36-dense",
        "destination": "/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9",
        "read_only": true
      }
    ],
    "original_runtime_signature": "cdb936a690a38f501fd5f4b24a48aad3704d29f2e9be80a43e81a2986c52ab30",
    "differences_from_original": [
      "Fresh container name and empty cache/result paths.",
      "Model inputs are individually bound read-only at the original container paths; only verified inputs are exposed.",
      "HF_HUB_OFFLINE=1 prevents public repository changes. For originally unpinned GGUF tokenizers, the delivered cache reference explicitly binds revision 6a9e13bd6fc8f0983b9b99948120bc37f49c13e9. This is a new pinned reproduction, not proof of the original unrecorded tokenizer selection."
    ],
    "gpu_test_status": "pending",
    "cpu_affinity": "No Docker cpuset in original; host default affinity retained.",
    "port": 8078,
    "proxy_port": 19078,
    "input_package": "historical-reproduction-r3.tar.gz"
  },
  "actual_launch_contract": {
    "all_explicit_Docker_arguments_match_actual_inspect": true,
    "verified_bind_mounts": 7,
    "verified_explicit_environment": 4
  },
  "memory_log_observations": {
    "model_load_delta_GiB": [
      {
        "line": 723,
        "text": "2026-11-08T22:59:57.180783513Z (Worker pid=327) (Worker_TP0 pid=327) INFO 11-08 22:59:57 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 9.563808 seconds",
        "values": [
          "6.84"
        ]
      }
    ],
    "available_KV_GiB": [
      {
        "line": 1271,
        "text": "2026-11-08T23:01:39.506595611Z (Worker pid=327) (Worker_TP0 pid=327) INFO 11-08 23:01:39 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB",
        "values": [
          "22.64"
        ]
      }
    ],
    "grouped_GPU_KV_tokens": [
      {
        "line": 1284,
        "text": "2026-11-08T23:01:40.213405262Z (EngineCore_DP0 pid=273) INFO 11-08 23:01:40 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens",
        "values": [
          "370,864"
        ]
      }
    ],
    "context_capacity": [
      {
        "line": 1285,
        "text": "2026-11-08T23:01:40.213475072Z (EngineCore_DP0 pid=273) INFO 11-08 23:01:40 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x",
        "values": [
          "131,072",
          "11.25"
        ]
      }
    ]
  },
  "tiers": {
    "warmup1": {
      "completion_tokens": 2000,
      "decode_tps": 71.34717518193268,
      "prefill_seconds": 193.95681127812713,
      "client_total_seconds": 222.01710358820856,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 193.95681127812713,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.031943730078638
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "df0582cdf91025cd95cfaddc6aafc981956e09354e3c4f8b3a2c1488ef84386e"
    },
    "warmup2": {
      "completion_tokens": 2000,
      "decode_tps": 71.31617203484386,
      "prefill_seconds": 15.438185648992658,
      "client_total_seconds": 43.491359625943005,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 15.438185648992658,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.044130004942417
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "fb5c875ca0b9616a130cd51f0580e1443b2d4d2cdceb45cbfa03a7d170ace8b2"
    },
    "warmup3": {
      "completion_tokens": 2000,
      "decode_tps": 71.3887499724801,
      "prefill_seconds": 13.507014341652393,
      "client_total_seconds": 41.531406439840794,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.507014341652393,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.015618718229234
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "45a345e99b346076acb7b52e840ee1f543900cca363cf27d2c2021135215dbb6"
    },
    "warmup4": {
      "completion_tokens": 2000,
      "decode_tps": 71.34972125092118,
      "prefill_seconds": 14.082540526986122,
      "client_total_seconds": 42.12210353370756,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 14.082540526986122,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.03094342816621
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "b0f234a4f1a8ffccbe7b0e6d235f76fd52269c8c5033034c8ac94b0e288585db"
    },
    "warmup5": {
      "completion_tokens": 2000,
      "decode_tps": 71.35821769745708,
      "prefill_seconds": 13.29047758411616,
      "client_total_seconds": 41.3262222725898,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.29047758411616,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.027605853043497
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "d1342e96ef46015b4e63ec3ebb8217cf01e0b7d576ccfc2caeb8c608a705eb4b"
    },
    "warmup6": {
      "completion_tokens": 2000,
      "decode_tps": 71.34205315258205,
      "prefill_seconds": 13.750972772017121,
      "client_total_seconds": 41.79387015290558,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.750972772017121,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.033956293947995
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "9daa805ede07d809d8c8d0960fb6547a5d033d301afc1f745dc308cf602e6971"
    },
    "warmup7": {
      "completion_tokens": 2000,
      "decode_tps": 71.35503929300538,
      "prefill_seconds": 13.717534556053579,
      "client_total_seconds": 41.755142574198544,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.717534556053579,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.028854301199317
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "5796e5ad58e3024f5687afecd11984e335804273777df45a74858406b31711db"
    },
    "warmup8": {
      "completion_tokens": 2000,
      "decode_tps": 71.33975272927218,
      "prefill_seconds": 13.7463249694556,
      "client_total_seconds": 41.789582141675055,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.7463249694556,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.034860277548432
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "32b72ce661eabfc7e42a3a1ca979ce794f8821a66937d3dbd3f89cd5bddf1635"
    },
    "strict": {
      "completion_tokens": 3894,
      "decode_tps": 70.29589397473099,
      "prefill_seconds": 14.098794215358794,
      "client_total_seconds": 69.50212777592242,
      "strict_pass": true,
      "finish_reason": "stop",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 3894.0,
        "vllm:request_prefill_time_seconds_sum": 14.098794215358794,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 55.39441608637571
      },
      "request_sha256": "d6b5acc7f81647ef18db224f701221c1f68a009b4548f6849cf87c3c8e419a9a",
      "summary_sha256": "7edb828e4d7722b0c1fd383897c084e95cdb225e7c5a037b23b28761ada4bc47"
    },
    "2K": {
      "completion_tokens": 2000,
      "decode_tps": 71.35954591433956,
      "prefill_seconds": 13.803319579921663,
      "client_total_seconds": 41.83979881927371,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 2000.0,
        "vllm:request_prefill_time_seconds_sum": 13.803319579921663,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.02708417456597
      },
      "request_sha256": "3d137c416021d94f838f557d4f42b0fbfe62d81a216b8c0a16b65a1f529aca97",
      "summary_sha256": "35b66db175a416934d4cd1895d171f23baa26dd6de6eeecc1ae3c60ef2905b15"
    },
    "10K": {
      "completion_tokens": 10000,
      "decode_tps": 66.82477816892438,
      "prefill_seconds": 14.576330919750035,
      "client_total_seconds": 164.2314986139536,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:generation_tokens_total": 10000.0,
        "vllm:request_prefill_time_seconds_sum": 14.576330919750035,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_decode_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 149.64509084820747
      },
      "request_sha256": "d03cae7830251b8462de5cfc7ed217442c2137d550fefb2baf4f6c92b612c39a",
      "summary_sha256": "09a50ce3034dc4380f7c301323163264cf522177a86be5b4be1fa6e0bdcbc20c"
    }
  },
  "auditor_replay": {
    "strict": {
      "exit": 0,
      "server_exit_matches": true,
      "stdout_sha256": "8cd02ba8b8f788daa227db45c02c1d2f535ecdc1d298c4b35c1bc209c3d0c933",
      "stderr_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    },
    "fixed": {
      "exit": 0,
      "server_exit_matches": true,
      "stdout_sha256": "d1918d9772e66642c9886b0848a3210df07a242cca00fe860f9c140e5cc2064c",
      "stderr_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    }
  },
  "eligible_historical_2K": true,
  "current_Qwen38_official_eligible": false,
  "archive_sha256": "bd4dd543e6aaf54bcc3962a7ce827255fce2b846cab5ad1245e24da58207c9d0",
  "archive_bytes": 66378099,
  "owner_retention_parent_exit": 0,
  "mirror_parent_exit": 0,
  "input_package": "historical-reproduction-r3.tar.gz",
  "input_package_sha256": "8c751c8c7607580bb58b9ed5005bf9b0cb59820bb0d90b8deff484c58c59691c",
  "image_archive": "gfx906-release-images.docker.tar.zst",
  "image_archive_sha256": "62f43b0328e4223420bf454ec769790c1d13c11c1c764071243d46f6e90b2715",
  "runtime_route_log_observations": {
    "scope": "Actual retained runtime messages, including shape-specific fast-path refusals and fallbacks. These are not a complete kernel execution trace or invocation count.",
    "source_log_sha256": "893e1179eb68944bb348b916fb21ae34b86996e1ad55797fcd7677a1d3cb2b1f",
    "lines": []
  },
  "route_log_review_utc": "2026-11-09T00:21:37.690013+00:00"
}
