{
  "profile": "v620-w4-tp2-mtp0",
  "image": "sha256:a16a6f2d47e7ac6ffc55d7a3d9298cad7e03601d8a30886421e905c92aeae386",
  "container": "63d508581fc91c4a06d201f732ab17b0e41917d68c06a98af7a60049e74f0225",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 25.59,
  "retest_logged_model_load_seconds": 114.199732,
  "retest_logged_available_KV_GiB": 1.05,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 1.05,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 7840,
  "retest_logged_context_capacity_x": 0.25,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w4-tp2-mtp0/service-final.log",
  "source_log_sha256": "1de293b6b62bc00ad5bad8ca7ae9b8602161b0137af4ffd056b3e51f09b244b3",
  "sealed_index_sha256": "d5b582c7896849a6be95b24fdc53dcdd4cecd5c8e248a63f69ae296aee7afd9d",
  "source_lines": {
    "model_load": {
      "line": 92,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 16:17:07 [gpu_model_runner.py:4579] Model loading took 25.59 GiB memory and 114.199732 seconds"
    },
    "automatic_KV_budget": {
      "line": 104,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 16:20:42 [gpu_worker.py:453] Available KV cache memory: 1.05 GiB"
    },
    "grouped_KV_tokens": {
      "line": 107,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 16:20:42 [kv_cache_utils.py:1314] GPU KV cache size: 7,840 tokens"
    },
    "context_capacity": {
      "line": 108,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 16:20:42 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 0.25x"
    }
  },
  "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."
}
