{
  "row": 35,
  "utc": "2026-11-08T23:59:10.041781+00:00",
  "image": "sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568",
  "container": "e42e507f95ad054742fcfeaf72b58d35f39a8db2a5c2f0525cf7e77bcc043af0",
  "runner_exit": 0,
  "manifest_sha256": "a96218fee0c78b5145db76c43cdf273ff01d169be52e0662ddcc70106f936f79",
  "verified_regular_files": 173,
  "closure": {
    "Status": "exited",
    "Running": false,
    "Paused": false,
    "Restarting": false,
    "OOMKilled": false,
    "Dead": false,
    "Pid": 0,
    "ExitCode": 137,
    "Error": "",
    "StartedAt": "2026-11-08T23:40:06.929336115Z",
    "FinishedAt": "2026-11-08T23:58:45.910937408Z"
  },
  "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": "7bc6e16b92d4443e253409524d0aca0ed65d132d37a8a697a04d7eac71291bcb",
    "installed_files": 55,
    "CPU_probe_contract_sha256": "10446a96fa7e57f4dd379870348c4ba8ba4b36a7964b356b839aa06fa245b719",
    "actual_worker_PIDs_by_TP_rank": {
      "0": 202,
      "1": 203,
      "2": 204,
      "3": 205,
      "4": 206,
      "5": 207,
      "6": 208,
      "7": 209
    }
  },
  "runtime-after-ladder": {
    "sha256": "1d9b6e910317fe0763afa89e34dca07899556f7f01ab881f57c2c73d58ea7de0",
    "installed_files": 55,
    "CPU_probe_contract_sha256": "10446a96fa7e57f4dd379870348c4ba8ba4b36a7964b356b839aa06fa245b719",
    "actual_worker_PIDs_by_TP_rank": {
      "0": 202,
      "1": 203,
      "2": 204,
      "3": 205,
      "4": 206,
      "5": 207,
      "6": 208,
      "7": 209
    }
  },
  "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": 527,
    "first_utc": "2026-11-08T23:40:07.103894+00:00",
    "last_utc": "2026-11-08T23:57:42.948656+00:00",
    "devices": [
      {
        "render": 128,
        "pci": "0000:06:00.0",
        "sampled_max_vram_bytes": 33776762880,
        "minimum_vram_bytes": 60289024
      },
      {
        "render": 129,
        "pci": "0000:09:00.0",
        "sampled_max_vram_bytes": 33666486272,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 130,
        "pci": "0000:45:00.0",
        "sampled_max_vram_bytes": 33716842496,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 131,
        "pci": "0000:48:00.0",
        "sampled_max_vram_bytes": 33666523136,
        "minimum_vram_bytes": 10862592
      },
      {
        "render": 132,
        "pci": "0000:89:00.0",
        "sampled_max_vram_bytes": 33716817920,
        "minimum_vram_bytes": 10862592
      },
      {
        "render": 133,
        "pci": "0000:8c:00.0",
        "sampled_max_vram_bytes": 33666486272,
        "minimum_vram_bytes": 10858496
      },
      {
        "render": 134,
        "pci": "0000:c5:00.0",
        "sampled_max_vram_bytes": 33716846592,
        "minimum_vram_bytes": 10854400
      },
      {
        "render": 135,
        "pci": "0000:c8:00.0",
        "sampled_max_vram_bytes": 33666510848,
        "minimum_vram_bytes": 10862592
      }
    ]
  },
  "runtime_configuration_source": {
    "container_inspect_sha256": "c485790720c65b245a5e65d417c64dfc8fa09261900ad627176fa7dc9a89550b",
    "preflight_sha256": "c7ba5a1934434e6e2c84cfd0e81cfd9082aa87291a60a067983c2314d46fe381",
    "docker_run_sha256": "830f95926991dc947f19041f3eeb7d88c01124ddf51866bd57d050c6dc9dce5e",
    "effective_engine_log_lines": [
      {
        "line": 7,
        "text": "2026-11-08T23:40:33.975708289Z (APIServer pid=126) INFO 11-08 23:40:33 [utils.py:228] non-default args: {'model_tag': '/opt/local-models/qwen36-27b-hf', 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_coder', 'host': '0.0.0.0', 'port': 8001, 'model': '/opt/local-models/qwen36-27b-hf', 'trust_remote_code': True, 'dtype': 'half', 'max_model_len': 131072, 'served_model_name': ['Qwen3.6-27B'], '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": 48,
        "text": "2026-11-08T23:40:53.955546811Z (APIServer pid=126) INFO 11-08 23:40:53 [model.py:1562] Using max model len 131072"
      },
      {
        "line": 55,
        "text": "2026-11-08T23:41:16.817435165Z (EngineCore_DP0 pid=184) INFO 11-08 23:41:16 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-27b-hf', 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, 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': []}"
      }
    ]
  },
  "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": "aecab7bdb20afc04e69d5d57f514f7de10533a309d250dbfd6b957a6f22d1fa3",
    "lines": []
  },
  "prepared_plan": {
    "row": 35,
    "profile": "hf-dense27b-tp8",
    "container_name": "historical-row35-19c89bb202-reproduction",
    "root": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35",
    "models_root": "/usr/share/ollama/localaiservers-repro-models",
    "image": "sha256:45decd88eb7c10c0408327438e07c2a655e45cc7534f8b662e5c4089a6b88568",
    "docker_argv": [
      "docker",
      "run",
      "-d",
      "--name",
      "historical-row35-19c89bb202-reproduction",
      "--network",
      "host",
      "--ipc",
      "host",
      "--privileged",
      "--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-35/hf,dst=/root/.cache/huggingface",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/launch,dst=/runwork",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/vllm,dst=/root/.cache/vllm",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/triton,dst=/root/.triton",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/inductor,dst=/tmp/torchinductor_root",
      "--mount",
      "type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/overlay,dst=/opt/vllm_patch_bundle,readonly",
      "--mount",
      "type=bind,src=/usr/share/ollama/localaiservers-repro-models/qwen36-dense,dst=/opt/local-models/qwen36-27b-hf,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-row35-19c89bb202-reproduction \\\n  --network \\\n  host \\\n  --ipc \\\n  host \\\n  --privileged \\\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-35/hf,dst=/root/.cache/huggingface \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/launch,dst=/runwork \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/vllm,dst=/root/.cache/vllm \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/triton,dst=/root/.triton \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/inductor,dst=/tmp/torchinductor_root \\\n  --mount \\\n  type=bind,src=/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/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/qwen36-27b-hf,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-35/hf",
        "destination": "/root/.cache/huggingface",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/launch",
        "destination": "/runwork",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/vllm",
        "destination": "/root/.cache/vllm",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/triton",
        "destination": "/root/.triton",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/cache/inductor",
        "destination": "/tmp/torchinductor_root",
        "read_only": false
      },
      {
        "source": "/home/ai/localaiservers-historical-20261108-r3/benchmark-row-35/overlay",
        "destination": "/opt/vllm_patch_bundle",
        "read_only": true
      },
      {
        "source": "/usr/share/ollama/localaiservers-repro-models/qwen36-dense",
        "destination": "/opt/local-models/qwen36-27b-hf",
        "read_only": true
      }
    ],
    "original_runtime_signature": "45420cf3f26a82a2390c715e2efd52d0f6de5d195faf5a890b4dcdd16f9274f8",
    "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": 8001,
    "proxy_port": 19080,
    "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": 712,
        "text": "2026-11-08T23:42:07.039298012Z (Worker pid=202) (Worker_TP0 pid=202) INFO 11-08 23:42:07 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 22.869422 seconds",
        "values": [
          "6.84"
        ]
      }
    ],
    "available_KV_GiB": [
      {
        "line": 1267,
        "text": "2026-11-08T23:43:52.218209587Z (Worker pid=202) (Worker_TP0 pid=202) INFO 11-08 23:43:52 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB",
        "values": [
          "22.64"
        ]
      }
    ],
    "grouped_GPU_KV_tokens": [
      {
        "line": 1273,
        "text": "2026-11-08T23:43:52.553188353Z (EngineCore_DP0 pid=184) INFO 11-08 23:43:52 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens",
        "values": [
          "370,864"
        ]
      }
    ],
    "context_capacity": [
      {
        "line": 1274,
        "text": "2026-11-08T23:43:52.553263624Z (EngineCore_DP0 pid=184) INFO 11-08 23:43:52 [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": 70.98677283248631,
      "prefill_seconds": 195.23157712537795,
      "client_total_seconds": 223.43015933036804,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 195.23157712537795,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.174262897111475,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "bff8606756239b2462dd9e543ede0bfddfc0332a86e5d8f30d73bf9a4061d939"
    },
    "warmup2": {
      "completion_tokens": 2000,
      "decode_tps": 70.97070398040165,
      "prefill_seconds": 14.21013342961669,
      "client_total_seconds": 42.39895459357649,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.21013342961669,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.180641980841756,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "310460ea54dab2093d9b9749ce88b7bae8afb12ca40826a4ceeea644c46a9ecd"
    },
    "warmup3": {
      "completion_tokens": 2000,
      "decode_tps": 70.96456204779409,
      "prefill_seconds": 13.878107007592916,
      "client_total_seconds": 42.06911638844758,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 13.878107007592916,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.183080995455384,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "110ebf1428aa7bc341ab533aa9bb45cb9ecb1ee059ab581dc5b2e22d3ee97de8"
    },
    "warmup4": {
      "completion_tokens": 2000,
      "decode_tps": 70.96342076499333,
      "prefill_seconds": 14.331278159283102,
      "client_total_seconds": 42.52322509139776,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.331278159283102,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.18353425525129,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "20559c42e5e115228e8e137e9504c103ef54cab77d05df5ce60ff8673d2b5190"
    },
    "warmup5": {
      "completion_tokens": 2000,
      "decode_tps": 70.98851449818045,
      "prefill_seconds": 14.09548242483288,
      "client_total_seconds": 42.27742645703256,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.09548242483288,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.17357165645808,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "b2baae4b249910119d5397ff3df7f4000b6e4c8ef3eb642c39c82a034d587f33"
    },
    "warmup6": {
      "completion_tokens": 2000,
      "decode_tps": 70.95375051140161,
      "prefill_seconds": 14.859874436631799,
      "client_total_seconds": 43.055482188239694,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.859874436631799,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.187375376001,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "47d970033c5abc2abcdc31f316821d91ad2ceb4d661306e9cf26196834729594"
    },
    "warmup7": {
      "completion_tokens": 2000,
      "decode_tps": 70.9318518567532,
      "prefill_seconds": 14.13181122392416,
      "client_total_seconds": 42.336332311853766,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.13181122392416,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.196077610366046,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "cefe97e1cd7acde1c933ff1292d5480ee6d8f936779f881b2acc883be5ba9311"
    },
    "warmup8": {
      "completion_tokens": 2000,
      "decode_tps": 70.94254844553882,
      "prefill_seconds": 12.953190175816417,
      "client_total_seconds": 41.15360536891967,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 12.953190175816417,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.191826256923378,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "15b98de7fe0303aacad94fd3d92c9a5d365d38c4bd834542e977053ca102033e"
    },
    "strict": {
      "completion_tokens": 3609,
      "decode_tps": 70.06009773846488,
      "prefill_seconds": 12.782165881246328,
      "client_total_seconds": 64.30384199228138,
      "strict_pass": true,
      "finish_reason": "stop",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 3609.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 12.782165881246328,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 51.512917002663016,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "ee97c35547770515d3bd63d45b2557687a8278bbeb38ce72abbaad2fee0ab250",
      "summary_sha256": "6ae03f5709d05f854c0ff4b3e846b625d2d4a691aac551f35ae21d6a4b36c17e"
    },
    "2K": {
      "completion_tokens": 2000,
      "decode_tps": 70.95081153473755,
      "prefill_seconds": 15.072314956225455,
      "client_total_seconds": 43.269196966663,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 2000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 15.072314956225455,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 28.188542974181473,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "d476546705501abd0468f2fc6527e9ace49f732079e53b75abf7bcfb98635f44",
      "summary_sha256": "f70df1fbfc18c6af1f765a73663863bb438fbe1dd644049da3c9e283ae692d0e"
    },
    "10K": {
      "completion_tokens": 10000,
      "decode_tps": 66.46936099788869,
      "prefill_seconds": 14.515854343771935,
      "client_total_seconds": 164.97092120815068,
      "strict_pass": null,
      "finish_reason": "length",
      "raw_counter_deltas": {
        "vllm:generation_tokens_total": 10000.0,
        "vllm:prompt_tokens_total": 431.0,
        "vllm:request_prefill_time_seconds_sum": 14.515854343771935,
        "vllm:request_prefill_time_seconds_count": 1.0,
        "vllm:request_decode_time_seconds_sum": 150.4452555263415,
        "vllm:request_decode_time_seconds_count": 1.0
      },
      "request_sha256": "ee5df402413359190aaa7ed74f4a298f749233768156b8fc14f2ea4bef0e8017",
      "summary_sha256": "1dfc4acf114048076b24fd3ed43f4a13dd3800ec8892ff4352974a55fd56aba2"
    }
  },
  "auditor_replay": {
    "strict": {
      "exit": 0,
      "server_exit_matches": true,
      "stdout_sha256": "19792cc9afd173773c4431167c5ccbff1efc199d7a398d404e54183340dc0dd3",
      "stderr_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    },
    "fixed": {
      "exit": 0,
      "server_exit_matches": true,
      "stdout_sha256": "68a7c93415382737da36755d2be77d1ace823a8c3eef892ca551650a2456eede",
      "stderr_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    }
  },
  "eligible_historical_2K": true,
  "current_Qwen38_official_eligible": false,
  "archive_sha256": "d9ec853ef7ef3dc9da478dfd95bdb2303e6ca1425f743908b67848db54ee3ee9",
  "archive_bytes": 66323558,
  "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"
}
