{
  "profile": "v620-w4-tp4-mtp0",
  "image": "sha256:b97918608d83591ad38f818bb4e944b5aa8d7d2fa9df2f354d47f1db190d9fcb",
  "container": "c1f1d4225224fe57f881a4a2eea02bb60ad836c7c0e96adf895bcd78d6ec7694",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 13.47,
  "retest_logged_model_load_seconds": 59.703993,
  "retest_logged_available_KV_GiB": 13.76,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 13.76,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 225008,
  "retest_logged_context_capacity_x": 6.72,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w4-tp4-mtp0/service-final.log",
  "source_log_sha256": "0e0bfd459de2a7ef66c6f6225696c4722266fd04a763121e3bb1ebc028697ca3",
  "sealed_index_sha256": "30b88085c5128904cba9bfbad035f6f909fd5b6ae8920387bc8fd26a2807844b",
  "source_lines": {
    "model_load": {
      "line": 120,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 14:38:21 [gpu_model_runner.py:4579] Model loading took 13.47 GiB memory and 59.703993 seconds"
    },
    "automatic_KV_budget": {
      "line": 141,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 14:41:09 [gpu_worker.py:453] Available KV cache memory: 13.76 GiB"
    },
    "grouped_KV_tokens": {
      "line": 144,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 14:41:10 [kv_cache_utils.py:1314] GPU KV cache size: 225,008 tokens"
    },
    "context_capacity": {
      "line": 145,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 14:41:10 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 6.72x"
    }
  },
  "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."
}
