{
  "profile": "v620-w4-tp4-mtp0-x",
  "image": "sha256:23efb9f20a02e5b7bd69ed0004a7a1976d35ba728e4fd52f644b4645eadd5ed1",
  "container": "ec3518784deb32352092d77a2decf4d6324f174f83299da367262e1603a263bb",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 13.57,
  "retest_logged_model_load_seconds": 65.883079,
  "retest_logged_available_KV_GiB": 13.65,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 13.65,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 223440,
  "retest_logged_context_capacity_x": 6.67,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w4-tp4-mtp0-x/service-final.log",
  "source_log_sha256": "3ef08b7b4c885cc867a908039180b10d89226cb9991c59b40a34cce08d3cfc4c",
  "sealed_index_sha256": "f0b1471b89d3b00a16d5794a170ae274389ce3e0a9a1ca8f0b2ff7e9866e5f7e",
  "source_lines": {
    "model_load": {
      "line": 120,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-27 01:38:37 [gpu_model_runner.py:4579] Model loading took 13.57 GiB memory and 65.883079 seconds"
    },
    "automatic_KV_budget": {
      "line": 140,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-27 01:42:20 [gpu_worker.py:453] Available KV cache memory: 13.65 GiB"
    },
    "grouped_KV_tokens": {
      "line": 145,
      "text": "(EngineCore_DP0 pid=65) INFO 10-27 01:42:20 [kv_cache_utils.py:1314] GPU KV cache size: 223,440 tokens"
    },
    "context_capacity": {
      "line": 146,
      "text": "(EngineCore_DP0 pid=65) INFO 10-27 01:42:20 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 6.67x"
    }
  },
  "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."
}
