{ "device": "NVIDIA GeForce RTX 3090", "torch": "2.10.0+cu130", "K": 8, "steps": 1, "B": 1, "act_scale": 1.0, "inference": { "fp32": { "p50": 7.681, "p95": 9.426, "p99": 10.631, "max": 15.837 }, "fp16": { "p50": 8.309, "p95": 10.791, "p99": 12.031, "max": 12.322 }, "bf16": { "p50": 8.577, "p95": 11.057, "p99": 14.174, "max": 17.1 } }, "cycle": { "fp32": { "p50": 36.507, "p95": 43.688, "p99": 46.568, "max": 50.598 }, "fp16": { "p50": 36.162, "p95": 50.43, "p99": 55.598, "max": 57.043 } }, "output_deviation": { "fp16": { "act_max_abs": 0.002096, "act_p99_abs": 0.001059, "deg_max_abs": 0.005, "deg_p99_abs": 0.00219, "would_change_execution_order": false }, "bf16": { "act_max_abs": 0.017171, "act_p99_abs": 0.012661, "deg_max_abs": 0.03766, "deg_p99_abs": 0.03008, "would_change_execution_order": true } } }