{
  "profile": "v620-fp16-tp4-mtp0",
  "image": "sha256:71f0e460e6327c9b3c5edcc90ff104e43ac14089883164c8bad20e9b141d1aeb",
  "container": "7d983ace8802d4bb9a7baa53f5380cf5063ccfa287413bae5200b7410067fd7b",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 19.34,
  "retest_logged_model_load_seconds": 102.409229,
  "retest_logged_available_KV_GiB": 7.92,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 7.92,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 129360,
  "retest_logged_context_capacity_x": 3.87,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-fp16-tp4-mtp0/service-final.log",
  "source_log_sha256": "2105e2e2c71b1f1c486467df44c1e3bb7f21fcf1728f97336882c12f7f9fca2f",
  "sealed_index_sha256": "0e7d2dc4efd36ed79cc775fbbcb19e362de1cd83ef6d074fe33e79bd4bcd296a",
  "source_lines": {
    "model_load": {
      "line": 851,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 21:39:20 [gpu_model_runner.py:4579] Model loading took 19.34 GiB memory and 102.409229 seconds"
    },
    "automatic_KV_budget": {
      "line": 938,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 21:43:38 [gpu_worker.py:453] Available KV cache memory: 7.92 GiB"
    },
    "grouped_KV_tokens": {
      "line": 943,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 21:43:39 [kv_cache_utils.py:1314] GPU KV cache size: 129,360 tokens"
    },
    "context_capacity": {
      "line": 944,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 21:43:39 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 3.87x"
    }
  },
  "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."
}
