{ "smoke": { "items": 96, "prediction_agreement": 0.9791666666666666, "max_probability_delta": 0.2923086923258452, "mean_probability_delta": 0.009561798528451486, "reference": "Previous full matched FP8 benchmark; same source revisions and export recipe", "concurrency": 64 }, "full_benchmark": { "metrics": { "korean": { "items": 25418, "views": 25418, "accuracy": 0.9215516563065544, "answer_disagreement": 0.0, "order_agreement": 1.0, "js": 0.0, "both_wrong_items": 1994, "concurrency": 128, "seconds": 136.16059323586524, "decisions_per_second": 186.67662497599048, "service_p50_ms": 125.52499771118164, "service_p95_ms": 182.70281553268424, "http_p50_ms": 685.1250806357712, "scheduler_queue_p50_ms": 484.1857466381043, "latency_metric_excludes_initial_server_queue": true, "warmup_included": false, "failures": 0 }, "english": { "items": 12032, "views": 12032, "accuracy": 0.6565824468085106, "answer_disagreement": 0.0, "order_agreement": 1.0, "js": 0.0, "both_wrong_items": 4132, "concurrency": 128, "seconds": 78.06261895876378, "decisions_per_second": 154.13267144362462, "service_p50_ms": 121.21415138244629, "service_p95_ms": 180.46717643737773, "http_p50_ms": 819.7654015384614, "scheduler_queue_p50_ms": 633.3689622115344, "latency_metric_excludes_initial_server_queue": true, "warmup_included": false, "failures": 0 }, "validation": { "items": 1259, "views": 2518, "accuracy": 0.8030182684670373, "answer_disagreement": 0.11358220810166798, "order_agreement": 0.886417791898332, "js": 0.023084942771858654, "both_wrong_items": 196, "concurrency": 16, "seconds": 55.61233388166875, "decisions_per_second": 45.27772571742395, "service_p50_ms": 123.31819534301758, "service_p95_ms": 195.64812183380127, "http_p50_ms": 423.17572492174804, "scheduler_queue_p50_ms": 188.92357125878334, "latency_metric_excludes_initial_server_queue": true, "warmup_included": false, "failures": 0 } }, "concurrency_search": { "selected": { "concurrency": 128, "runs": 2, "median_decisions_per_second": 190.1530961114044, "median_service_p50_ms": 121.40101194381714 }, "aggregates": [ { "concurrency": 1, "runs": 1, "median_decisions_per_second": 16.194536650870774, "median_service_p50_ms": 50.647735595703125 }, { "concurrency": 8, "runs": 1, "median_decisions_per_second": 45.94295835264903, "median_service_p50_ms": 111.7018461227417 }, { "concurrency": 32, "runs": 1, "median_decisions_per_second": 158.20845752359367, "median_service_p50_ms": 117.02775955200195 }, { "concurrency": 64, "runs": 1, "median_decisions_per_second": 185.02005123015408, "median_service_p50_ms": 126.47759914398193 }, { "concurrency": 128, "runs": 2, "median_decisions_per_second": 190.1530961114044, "median_service_p50_ms": 121.40101194381714 }, { "concurrency": 256, "runs": 2, "median_decisions_per_second": 189.78770785828365, "median_service_p50_ms": 121.05685472488403 }, { "concurrency": 512, "runs": 1, "median_decisions_per_second": 187.9789270075793, "median_service_p50_ms": 121.22511863708496 } ], "uses_gold": false, "workload_items": 2048, "claim": "Best observed tested concurrency; top two repeated. Service p50 from same trials, initial server queue excluded." }, "model": { "key": "korjev-26b4a-v1", "label": "korjev-26b4a-v1", "model": "google/gemma-4-26B-A4B-it", "revision": "4d7ae4984b7db7de8f8457170b3f1a419ee76d52", "precision": "FP8", "export": true, "adapter": { "repo": "DaehanKim/korean-jev-gemma4-26b-v7-ce-js-kl", "revision": "488603ea86c59531b0870c8aee50ee43d0002af4", "subfolder": "epoch-1.0" }, "checkpoint": "KL epoch 1.0", "active_parameters_billion": 3.8, "parameter_source": "https://huggingface.co/google/gemma-4-26B-A4B-it" }, "weights_or_recipe_selected_using_tests": false, "training": false }, "tensor_count": 24198, "tensor_dtype_counts": { "BF16": 12473, "F8_E4M3": 11725 }, "example_passed": true, "sglang_version": "0.5.21" }