{
  "profile": "v620-w8-tp2-mtp2",
  "image": "sha256:eaf8fffc828de2bb017493048c35a81a22b96964ca4852af5732cf17d6f38567",
  "container": "21a9828f12b1d34b82e2d0a87d86fb0d50ba8af66ac161c5ef4070a0e8424ed6",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 16.56,
  "retest_logged_model_load_seconds": 123.006295,
  "retest_logged_available_KV_GiB": 9.6,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 9.6,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 73600,
  "retest_logged_context_capacity_x": 2.14,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w8-tp2-mtp2/service-final.log",
  "source_log_sha256": "55ab409a441ae421f1d1b05f492f45e5125d690e7dcbd2140e32c403b07075c4",
  "sealed_index_sha256": "80034e3ab771353bf7a27f0c11c3a059a53363a207eb153ed442827132adb6d0",
  "source_lines": {
    "model_load": {
      "line": 118,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 20:37:10 [gpu_model_runner.py:4598] Model loading took 16.56 GiB memory and 123.006295 seconds"
    },
    "automatic_KV_budget": {
      "line": 172,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 20:57:42 [gpu_worker.py:453] Available KV cache memory: 9.6 GiB"
    },
    "grouped_KV_tokens": {
      "line": 176,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 20:57:42 [kv_cache_utils.py:1314] GPU KV cache size: 73,600 tokens"
    },
    "context_capacity": {
      "line": 177,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 20:57:42 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 2.14x"
    }
  },
  "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."
}
