{
  "profile": "mi50-fp16-tp4-mtp0",
  "image": "sha256:5c4e7b7a071d89eee0e8941aa9f9a857b687864ee7bb5d9d59eb7cc50ff48c04",
  "container": "c8c0b898e9d81627eee172f20ca0783b4e5a809246b93619c4230e06528aae37",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 22.81,
  "retest_logged_model_load_seconds": 67.548319,
  "retest_logged_available_KV_GiB": 6.53,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 6.53,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 106800,
  "retest_logged_context_capacity_x": 3.23,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-fp16-tp4-mtp0/service-final.log",
  "source_log_sha256": "b6ce15ca515eb9d0dd6c076e8574f46fd917d7b27ba414136defce7cc7e4b42d",
  "sealed_index_sha256": "352796834416d1920746822000adb67699cb30990ae230cd3e920799f86c1230",
  "source_lines": {
    "model_load": {
      "line": 1161,
      "text": "(Worker pid=197) (Worker_TP0 pid=197) INFO 10-26 20:32:47 [gpu_model_runner.py:4584] Model loading took 22.81 GiB memory and 67.548319 seconds"
    },
    "automatic_KV_budget": {
      "line": 1240,
      "text": "(Worker pid=197) (Worker_TP0 pid=197) INFO 10-26 20:34:54 [gpu_worker.py:453] Available KV cache memory: 6.53 GiB"
    },
    "grouped_KV_tokens": {
      "line": 1245,
      "text": "(EngineCore_DP0 pid=179) INFO 10-26 20:34:54 [kv_cache_utils.py:1314] GPU KV cache size: 106,800 tokens"
    },
    "context_capacity": {
      "line": 1246,
      "text": "(EngineCore_DP0 pid=179) INFO 10-26 20:34:54 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 3.23x"
    }
  },
  "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."
}
