| { |
| "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 |
| } |
| } |
|
|
