{
  "profile": "mi50-fp16-tp8-mtp0",
  "image": "sha256:0aab9fc8441d0d25b576bdb70ef0c9cbb6982eb7ac37a7f108fee2dba77a40ce",
  "container": "ae82bff4b20a076f77a910c5721aa5ac0fc946b40a75fd1ab511e08b08f418aa",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 9.07,
  "retest_logged_model_load_seconds": 22.691548,
  "retest_logged_available_KV_GiB": 20.57,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 20.57,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 336752,
  "retest_logged_context_capacity_x": 10.22,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-fp16-tp8-mtp0/service-final.log",
  "source_log_sha256": "73b42cdf85e17a4b8fc446101f58a84f60f280529af15dc1711fd4dada425b46",
  "sealed_index_sha256": "4578ad1dc43c02e27e9e24e23f5962720d6906c26ef4715afe24cb4f342f5279",
  "source_lines": {
    "model_load": {
      "line": 216,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 15:59:42 [gpu_model_runner.py:4584] Model loading took 9.07 GiB memory and 22.691548 seconds"
    },
    "automatic_KV_budget": {
      "line": 267,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:02:06 [gpu_worker.py:453] Available KV cache memory: 20.57 GiB"
    },
    "grouped_KV_tokens": {
      "line": 274,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:02:06 [kv_cache_utils.py:1314] GPU KV cache size: 336,752 tokens"
    },
    "context_capacity": {
      "line": 275,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:02:06 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 10.22x"
    }
  },
  "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."
}
