{
  "profile": "v620-w8-tp4-mtp2",
  "image": "sha256:eaf8fffc828de2bb017493048c35a81a22b96964ca4852af5732cf17d6f38567",
  "container": "5457bd41fa75f10e8266c62e7d825106f9d861c3a122df35c891d462aff0ef09",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 8.25,
  "retest_logged_model_load_seconds": 69.672332,
  "retest_logged_available_KV_GiB": 18.53,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 18.53,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 284800,
  "retest_logged_context_capacity_x": 8.25,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w8-tp4-mtp2/service-final.log",
  "source_log_sha256": "196a6879d46ceafafa4327fa2e08df4d40d490907a2174e6abe1f3d38e50358f",
  "sealed_index_sha256": "02fc37701b599060b58b02a78ac7165d21c59bda1893085577c5b7228fd3431e",
  "source_lines": {
    "model_load": {
      "line": 154,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 19:44:59 [gpu_model_runner.py:4598] Model loading took 8.25 GiB memory and 69.672332 seconds"
    },
    "automatic_KV_budget": {
      "line": 225,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 20:02:31 [gpu_worker.py:453] Available KV cache memory: 18.53 GiB"
    },
    "grouped_KV_tokens": {
      "line": 229,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 20:02:31 [kv_cache_utils.py:1314] GPU KV cache size: 284,800 tokens"
    },
    "context_capacity": {
      "line": 230,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 20:02:31 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 8.25x"
    }
  },
  "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."
}
