{
  "profile": "mi50-w4-tp8-mtp0",
  "image": "sha256:89bf56371852ba69e2dc3375fb1f667fe11f2a34a04537beb6ab75da4173c5c7",
  "container": "5e1221480e5b4d81ce3a4f5f513c0a5aff435c64a9b4f7378fa2e683791bd435",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 6.94,
  "retest_logged_model_load_seconds": 16.603594,
  "retest_logged_available_KV_GiB": 22.54,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 22.54,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 368800,
  "retest_logged_context_capacity_x": 11.15,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-w4-tp8-mtp0/service-final.log",
  "source_log_sha256": "3d3066110fccc8799355e5183fb3c1bfc2e9bb090c058a66fc4a945252e9f2fe",
  "sealed_index_sha256": "65edaba46ff0169318729d56558f624b0a3c954f850ea69f7848b5e0aa401997",
  "source_lines": {
    "model_load": {
      "line": 196,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:22:57 [gpu_model_runner.py:4584] Model loading took 6.94 GiB memory and 16.603594 seconds"
    },
    "automatic_KV_budget": {
      "line": 237,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:24:03 [gpu_worker.py:453] Available KV cache memory: 22.54 GiB"
    },
    "grouped_KV_tokens": {
      "line": 243,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:24:03 [kv_cache_utils.py:1314] GPU KV cache size: 368,800 tokens"
    },
    "context_capacity": {
      "line": 244,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:24:03 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.15x"
    }
  },
  "limits": "Model-load delta and automatic available-KV values are rounded engine reports, not measured physical VRAM or exact tensor-byte totals. Explicit budgets are configuration values confirmed in the loaded engine, not profiled availability. Grouped KV tokens and concurrency use the engine hybrid-cache accounting; they are not proof of a completed full-context request or an exact request ceiling."
}
