{
  "profile": "v620-w8-tp2-mtp0",
  "image": "sha256:95626d8b1e5b583a5348b5e7c9a0cd91840877eb5e3407e916f53298f80cf9f6",
  "container": "c3d8022dd7ce5fa8e2e24216effa6f2440fdfff5db6759f71cebf69280de0bc9",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 25.74,
  "retest_logged_model_load_seconds": 120.96945,
  "retest_logged_available_KV_GiB": 0.89,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 0.89,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 7056,
  "retest_logged_context_capacity_x": 0.22,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w8-tp2-mtp0/service-final.log",
  "source_log_sha256": "76f146dedd1427413c72a2fddf5bb88dc8157ba19bbd406d8e4f3a661b4da0eb",
  "sealed_index_sha256": "b39dd2de284da65749c1d6bee3a8772a4ccc714135b8ce6dc83ff8ec1f7d42e1",
  "source_lines": {
    "model_load": {
      "line": 92,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 18:45:06 [gpu_model_runner.py:4598] Model loading took 25.74 GiB memory and 120.969450 seconds"
    },
    "automatic_KV_budget": {
      "line": 105,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 18:48:53 [gpu_worker.py:453] Available KV cache memory: 0.89 GiB"
    },
    "grouped_KV_tokens": {
      "line": 107,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 18:48:53 [kv_cache_utils.py:1314] GPU KV cache size: 7,056 tokens"
    },
    "context_capacity": {
      "line": 108,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 18:48:53 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 0.22x"
    }
  },
  "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."
}
