{
  "schema": "daecore.serving-preparation-summary.v1",
  "date": "2026-09-28",
  "hardware": "Windows x64, NVIDIA RTX 3060 Ti 8 GiB",
  "unmeasured_targets": [
    "AMD",
    "Intel",
    "Linux x64"
  ],
  "runtimes": {
    "onnxruntime": "1.24.4",
    "vulkan_plugin": "0.4.0",
    "backend": "Vulkan",
    "storage_buffer_cache": "lazyRelease"
  },
  "model": "ettin",
  "qualification": {
    "queries": 970,
    "unjudged_top20": 0,
    "quality_evidence": "serving.json",
    "quality_receipt_sha256": "805a1b0acd7baaf248e182908bc23cd52171e40aa8f1281799a20d15b58c6905",
    "full_replay_seconds_p50_p95": [
      1.7189999999827705,
      2.610000000044238
    ],
    "matched_20_pool_seconds_p50_p95": {
      "vulkan": [
        1.5565476999909151,
        2.1063475799834124
      ],
      "predecessor_directml": [
        1.9197023500164505,
        2.701977299965802
      ]
    },
    "pressure": "One preflight refusal after 322 queries with lazy release; resumed all remaining rows with zero further retries. An earlier default-cache run stopped after 424. No native OOM observed.",
    "precision": "FP32 Vulkan versus FP16 CUDA; rankings not bit-exact",
    "selector": "The provider comparison transfers the preceding CUDA mapping; it does not measure the newly fitted release mapping."
  },
  "worker_recovery": {
    "receipt_sha256": "46205d39521bde40d1228c837e57f88e1a941d42f6846f4a244c48b513347cc6",
    "outputs_identical_after_owned_worker_crash": true
  },
  "public_reranking": {
    "scope": "Retained matched public pools retrieved by upstream Gemma; upstream and production Ettin PyTorch FP16; not a new Vulkan public replay",
    "source_sha256": "0814db560081af8376e4b1f3e3d2bcd5c4d9b8b208f7fb8b7172f113e8123ef3",
    "panels": {
      "fiqa": {
        "queries": 648,
        "ndcg@10": {
          "upstream": 0.48603492061219766,
          "finetuned": 0.452680922415071
        }
      },
      "scifact": {
        "queries": 300,
        "ndcg@10": {
          "upstream": 0.7487436478294831,
          "finetuned": 0.7543833016238701
        }
      }
    }
  },
  "maximum_envelope": {
    "tokens": 1153,
    "max_abs_logit_delta_vs_cpu": 5.91278076171875e-05
  }
}