{
  "profile": "mi50-w8-tp4-mtp0",
  "image": "sha256:1cdbeac5f8956a3068a57f28acd7f9dd2a4aa4de590cb90d8db25606f19db24a",
  "container": "5a3463ca7a0d4134be09562c677c092b3a8f8952eb1d9d6f0f6a24795e966fc0",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 13.25,
  "retest_logged_model_load_seconds": 64.44897,
  "retest_logged_available_KV_GiB": 15.92,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 15.92,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 260288,
  "retest_logged_context_capacity_x": 7.77,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-w8-tp4-mtp0/service-final.log",
  "source_log_sha256": "00785c973ab4b2f5244959832bc6928c3b8483fd02cedd719bad4475c078b8b4",
  "sealed_index_sha256": "6bf9c86f222b1baf9d1e5e4e47cf58baa38ee70a9f0b2006431655307d80db75",
  "source_lines": {
    "model_load": {
      "line": 144,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 15:33:02 [gpu_model_runner.py:4584] Model loading took 13.25 GiB memory and 64.448970 seconds"
    },
    "automatic_KV_budget": {
      "line": 166,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 15:34:08 [gpu_worker.py:453] Available KV cache memory: 15.92 GiB"
    },
    "grouped_KV_tokens": {
      "line": 171,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 15:34:08 [kv_cache_utils.py:1314] GPU KV cache size: 260,288 tokens"
    },
    "context_capacity": {
      "line": 172,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 15:34:08 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 7.77x"
    }
  },
  "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."
}
