{
  "profile": "mi50-w4-tp4-mtp0",
  "image": "sha256:72f25a82297a6d478d4f4fee305b8c7853999edeb0c86d852b8370849f810fe3",
  "container": "562cda56103fb421e6adf66cd6726f7ba830c1f89fbcd0e042644e91a1d8e6e8",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 13.16,
  "retest_logged_model_load_seconds": 79.138209,
  "retest_logged_available_KV_GiB": 16.01,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 16.01,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 261856,
  "retest_logged_context_capacity_x": 7.82,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-w4-tp4-mtp0/service-final.log",
  "source_log_sha256": "82234bdbf1435b75c9834c4de1afa8954c2357b23180cc78f3c19bc1ab470fab",
  "sealed_index_sha256": "ce64d445ea0f358d6dcc1f3f3a09f310416abdf4782a992701442ea1c778834b",
  "source_lines": {
    "model_load": {
      "line": 144,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:10:29 [gpu_model_runner.py:4584] Model loading took 13.16 GiB memory and 79.138209 seconds"
    },
    "automatic_KV_budget": {
      "line": 167,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:11:47 [gpu_worker.py:453] Available KV cache memory: 16.01 GiB"
    },
    "grouped_KV_tokens": {
      "line": 171,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:11:47 [kv_cache_utils.py:1314] GPU KV cache size: 261,856 tokens"
    },
    "context_capacity": {
      "line": 172,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:11:47 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 7.82x"
    }
  },
  "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."
}
