{
  "profile": "v620-w4-tp4-mtp2",
  "image": "sha256:762cae7dd32e7f3542a57754b547742471c371a40d287a115ac349616ec64681",
  "container": "cb24d05f08e6f9ae6d34cb9601d716a131da7448c1b3cb35342c550e9caedbdd",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 5.51,
  "retest_logged_model_load_seconds": 60.300757,
  "retest_logged_available_KV_GiB": 21.24,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 21.24,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 327200,
  "retest_logged_context_capacity_x": 9.46,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w4-tp4-mtp2/service-final.log",
  "source_log_sha256": "0807c48469b50f3cc209a1eaa5f6f67d3306b2fc2d612248ef1f5e64527c26a5",
  "sealed_index_sha256": "fe7ba6674f7a15c60fd9db595447d9b2e0bb7728107d4990e709736e59b41617",
  "source_lines": {
    "model_load": {
      "line": 154,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 15:21:33 [gpu_model_runner.py:4598] Model loading took 5.51 GiB memory and 60.300757 seconds"
    },
    "automatic_KV_budget": {
      "line": 223,
      "text": "(Worker pid=103) (Worker_TP0 pid=103) INFO 10-26 15:38:24 [gpu_worker.py:453] Available KV cache memory: 21.24 GiB"
    },
    "grouped_KV_tokens": {
      "line": 228,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 15:38:24 [kv_cache_utils.py:1314] GPU KV cache size: 327,200 tokens"
    },
    "context_capacity": {
      "line": 229,
      "text": "(EngineCore_DP0 pid=85) INFO 10-26 15:38:24 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 9.46x"
    }
  },
  "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."
}
