{
  "profile": "v620-fp16-tp4-mtp2",
  "image": "sha256:470486980ed01b78334c8e0b3ae36c9396d0ac9d5dba1183d581a857fe95674d",
  "container": "ecc08d8c02c333ce0a0cbdc6b46ac5a15fc230cb1189ca255b88a68f07f03fd9",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 20.64,
  "retest_logged_model_load_seconds": 68.668489,
  "retest_logged_available_KV_GiB": 6.11,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 6.11,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 93600,
  "retest_logged_context_capacity_x": 2.72,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-fp16-tp4-mtp2/service-final.log",
  "source_log_sha256": "7b07a9c59e06465fab4a524d823a544a019ffd6d1da77b716d1da525392aaa3c",
  "sealed_index_sha256": "77ccd32707a78a1145f1917f797db402a47ad46148bc20fb5ff6f1af0a7821aa",
  "source_lines": {
    "model_load": {
      "line": 893,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 23:45:18 [gpu_model_runner.py:4579] Model loading took 20.64 GiB memory and 68.668489 seconds"
    },
    "automatic_KV_budget": {
      "line": 986,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-27 00:02:07 [gpu_worker.py:453] Available KV cache memory: 6.11 GiB"
    },
    "grouped_KV_tokens": {
      "line": 991,
      "text": "(EngineCore_DP0 pid=85) INFO 10-27 00:02:07 [kv_cache_utils.py:1314] GPU KV cache size: 93,600 tokens"
    },
    "context_capacity": {
      "line": 992,
      "text": "(EngineCore_DP0 pid=85) INFO 10-27 00:02:07 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 2.72x"
    }
  },
  "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."
}
