{
  "profile": "v620-w4-tp2-mtp2",
  "image": "sha256:7f987d7773de6755f27160795f693fb1374eb42f54f2f322e917432c0886fd84",
  "container": "70e39d1b172d119241eb03dbd6619fcb0c16edb72e4d6c821d31d0d3628f146b",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 10.97,
  "retest_logged_model_load_seconds": 106.4305,
  "retest_logged_available_KV_GiB": 15.19,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 15.19,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 116800,
  "retest_logged_context_capacity_x": 3.38,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w4-tp2-mtp2/service-final.log",
  "source_log_sha256": "38a702105b6b0ffe6eca92cfc94fe05a20949d83e51f76d0326d098ca29c1e05",
  "sealed_index_sha256": "89aaf41caccca05a57040a8728c276f5acab0ccd3fc718e6700e103b8e71b36e",
  "source_lines": {
    "model_load": {
      "line": 118,
      "text": "(Worker pid=102) (Worker_TP0 pid=102) INFO 10-26 17:05:15 [gpu_model_runner.py:4598] Model loading took 10.97 GiB memory and 106.430500 seconds"
    },
    "automatic_KV_budget": {
      "line": 168,
      "text": "(Worker pid=102) (Worker_TP0 pid=102) INFO 10-26 17:21:47 [gpu_worker.py:453] Available KV cache memory: 15.19 GiB"
    },
    "grouped_KV_tokens": {
      "line": 172,
      "text": "(EngineCore_DP0 pid=84) INFO 10-26 17:21:47 [kv_cache_utils.py:1314] GPU KV cache size: 116,800 tokens"
    },
    "context_capacity": {
      "line": 173,
      "text": "(EngineCore_DP0 pid=84) INFO 10-26 17:21:47 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 3.38x"
    }
  },
  "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."
}
