{
  "profile": "mi50-w8-tp4-mtp2",
  "image": "sha256:b1a99e7c6968d27022bfb22ad547a38e6be2b8c760db2e708e2c3d695546cbe7",
  "container": "2901da8586316a8b0a053199945a78afd8c877762f777773550bd1a8463cbba4",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 14.43,
  "retest_logged_model_load_seconds": 63.480969,
  "retest_logged_available_KV_GiB": 14.35,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 14.35,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 220800,
  "retest_logged_context_capacity_x": 6.39,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-w8-tp4-mtp2/service-final.log",
  "source_log_sha256": "37ad86fe2abc818ffd5877f746e3891fdfc6c948a6eec70e813d4b171a7d0e3d",
  "sealed_index_sha256": "cad06a029821c6b96a4260e7a9e1f3938969ecef85de855a0ab156d226b112e4",
  "source_lines": {
    "model_load": {
      "line": 178,
      "text": "(Worker pid=216) (Worker_TP0 pid=216) INFO 10-26 19:01:37 [gpu_model_runner.py:4584] Model loading took 14.43 GiB memory and 63.480969 seconds"
    },
    "automatic_KV_budget": {
      "line": 265,
      "text": "(Worker pid=216) (Worker_TP0 pid=216) INFO 10-26 19:06:40 [gpu_worker.py:453] Available KV cache memory: 14.35 GiB"
    },
    "grouped_KV_tokens": {
      "line": 269,
      "text": "(EngineCore_DP0 pid=198) INFO 10-26 19:06:40 [kv_cache_utils.py:1314] GPU KV cache size: 220,800 tokens"
    },
    "context_capacity": {
      "line": 270,
      "text": "(EngineCore_DP0 pid=198) INFO 10-26 19:06:40 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 6.39x"
    }
  },
  "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."
}
