{
  "profile": "mi50-fp16-tp4-mtp2",
  "image": "sha256:b6fa047585772ad215c9dd1cf6ff0a57dc37039743aab0637ace0753c20ff2e4",
  "container": "a6900dc2002295b8c6786cb3cbe72fc0905467b837eb0c385bd9c52d17f73453",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 24.18,
  "retest_logged_model_load_seconds": 82.437392,
  "retest_logged_available_KV_GiB": 4.79,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 4.79,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 73600,
  "retest_logged_context_capacity_x": 2.13,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-fp16-tp4-mtp2/service-final.log",
  "source_log_sha256": "01da5b75e4ef49cb1d7d6bc6ad0f0bedd32b3e985961684407826dc906561b9a",
  "sealed_index_sha256": "287b09e42de876cf580b22e48e3779b0b496040a93d8af8611dfe440da40deec",
  "source_lines": {
    "model_load": {
      "line": 1173,
      "text": "(Worker pid=216) (Worker_TP0 pid=216) INFO 10-26 21:03:21 [gpu_model_runner.py:4584] Model loading took 24.18 GiB memory and 82.437392 seconds"
    },
    "automatic_KV_budget": {
      "line": 1317,
      "text": "(Worker pid=216) (Worker_TP0 pid=216) INFO 10-26 21:09:19 [gpu_worker.py:453] Available KV cache memory: 4.79 GiB"
    },
    "grouped_KV_tokens": {
      "line": 1321,
      "text": "(EngineCore_DP0 pid=198) INFO 10-26 21:09:19 [kv_cache_utils.py:1314] GPU KV cache size: 73,600 tokens"
    },
    "context_capacity": {
      "line": 1322,
      "text": "(EngineCore_DP0 pid=198) INFO 10-26 21:09:19 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 2.13x"
    }
  },
  "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."
}
