{
  "profile": "v620-fp16-tp2-mtp0",
  "image": "sha256:83a139552fe2e33ba48844e32e69b83ac6d10c592cd0547dfdd1643eaad2408f",
  "container": "15339a206d6624e7abc9caab614f44169f6673d584ba35e9b55bb74a045adbff",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 25.39,
  "retest_logged_model_load_seconds": 15.697194,
  "retest_logged_available_KV_GiB": 1.24,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 1.24,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 9408,
  "retest_logged_context_capacity_x": 0.3,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-fp16-tp2-mtp0/service-final.log",
  "source_log_sha256": "f341d1fc02158cf2480d0571daa0c0d94ea5331083628a0a5fbf9f801b2669a9",
  "sealed_index_sha256": "cf2eb4f5955d369cad6634fb9728c17c9d89e4376c3fad6427c6d195add6bad7",
  "source_lines": {
    "model_load": {
      "line": 91,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 22:25:31 [gpu_model_runner.py:4579] Model loading took 25.39 GiB memory and 15.697194 seconds"
    },
    "automatic_KV_budget": {
      "line": 102,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 22:26:47 [gpu_worker.py:453] Available KV cache memory: 1.24 GiB"
    },
    "grouped_KV_tokens": {
      "line": 104,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 22:26:47 [kv_cache_utils.py:1314] GPU KV cache size: 9,408 tokens"
    },
    "context_capacity": {
      "line": 105,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 22:26:47 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 0.30x"
    }
  },
  "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."
}
