{
  "profile": "mi50-fp16-tp8-mtp0-previous",
  "image": "sha256:5c4e7b7a071d89eee0e8941aa9f9a857b687864ee7bb5d9d59eb7cc50ff48c04",
  "container": "8b859435de245533d593ce5501e9d10ad6d8dcc76d593b11ac845b427b5c56c2",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 6.82,
  "retest_logged_model_load_seconds": 7.578667,
  "retest_logged_available_KV_GiB": 22.67,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 22.67,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 371072,
  "retest_logged_context_capacity_x": 11.26,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-fp16-tp8-mtp0-previous/service-final.log",
  "source_log_sha256": "071c179f82976ea238ccede6a3e54f18071f17adf763c73baff256e6cfaa164f",
  "sealed_index_sha256": "36dc26d55a69b2bb0238dd8b67f921f2e7195d0d7794c8a7336849ac6cc94e73",
  "source_lines": {
    "model_load": {
      "line": 207,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 17:11:11 [gpu_model_runner.py:4584] Model loading took 6.82 GiB memory and 7.578667 seconds"
    },
    "automatic_KV_budget": {
      "line": 256,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 17:12:42 [gpu_worker.py:453] Available KV cache memory: 22.67 GiB"
    },
    "grouped_KV_tokens": {
      "line": 264,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 17:12:42 [kv_cache_utils.py:1314] GPU KV cache size: 371,072 tokens"
    },
    "context_capacity": {
      "line": 265,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 17:12:42 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.26x"
    }
  },
  "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."
}
