{
  "profile": "v620-fp16-tp2-mtp2",
  "image": "sha256:a98060dd75e701abc267843ccd7d8513c7baf7b6abb168c6c289bd2dbad5d399",
  "container": "7da02e7c6d52440d7406b6ae5c7c29a90753fa6e5d16e0fe3656656a0ab9b989",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 25.76,
  "retest_logged_model_load_seconds": 15.149719,
  "retest_logged_available_KV_GiB": 0.36,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 0.36,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 2400,
  "retest_logged_context_capacity_x": 0.08,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-fp16-tp2-mtp2/service-final.log",
  "source_log_sha256": "3b8d72488fed8ca3839b7289454b1ea79619e1f6c0abe3566f286e7a5231fe0a",
  "sealed_index_sha256": "ec69fada416a475bb7eb71d8a77a656e3a1b45000a1dec03b45a57191a86dc0b",
  "source_lines": {
    "model_load": {
      "line": 117,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-27 02:20:55 [gpu_model_runner.py:4604] Model loading took 25.76 GiB memory and 15.149719 seconds"
    },
    "automatic_KV_budget": {
      "line": 167,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-27 02:36:10 [gpu_worker.py:453] Available KV cache memory: 0.36 GiB"
    },
    "grouped_KV_tokens": {
      "line": 170,
      "text": "(EngineCore_DP0 pid=85) INFO 10-27 02:36:10 [kv_cache_utils.py:1314] GPU KV cache size: 2,400 tokens"
    },
    "context_capacity": {
      "line": 171,
      "text": "(EngineCore_DP0 pid=85) INFO 10-27 02:36:10 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 0.08x"
    }
  },
  "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."
}
