{
  "profile": "mi50-w8-tp8-mtp0",
  "image": "sha256:89bf56371852ba69e2dc3375fb1f667fe11f2a34a04537beb6ab75da4173c5c7",
  "container": "c61c4fe370d271c8db3d197080e59e6d5b1f4dacc57b36c94291766d55ea0e1f",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 6.95,
  "retest_logged_model_load_seconds": 17.205276,
  "retest_logged_available_KV_GiB": 22.52,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 22.52,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 368800,
  "retest_logged_context_capacity_x": 11.14,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-w8-tp8-mtp0/service-final.log",
  "source_log_sha256": "dcee58767022051e10ffee4de33d2fdcc25ce21dcdc0a9f7092717ef867728eb",
  "sealed_index_sha256": "21dc9b4b2d45cc245fe333cd4281f9c38eca3601458bec384de9e343d1c62f9a",
  "source_lines": {
    "model_load": {
      "line": 196,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:45:52 [gpu_model_runner.py:4584] Model loading took 6.95 GiB memory and 17.205276 seconds"
    },
    "automatic_KV_budget": {
      "line": 236,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 16:46:57 [gpu_worker.py:453] Available KV cache memory: 22.52 GiB"
    },
    "grouped_KV_tokens": {
      "line": 243,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:46:57 [kv_cache_utils.py:1314] GPU KV cache size: 368,800 tokens"
    },
    "context_capacity": {
      "line": 244,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 16:46:57 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.14x"
    }
  },
  "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."
}
