{ "gpu": "NVIDIA GeForce RTX 4090", "torch": "2.14.1+cu130", "dtype": "fp32 weights + bf16 autocast", "batch_size": 1, "warmup": 100, "measured": 1000, "inputs": "test_idd, seed 0 (labels unused)", "software": { "laya": "0.3.28", "transformers": "4.57.6", "cuda": "13.0" }, "questions_per_step": "operation + target (all candidates), one forward", "max_len": 3072, "head_max_len": 1536, "models": { "laya_android": { "forward_ms": { "n": 1000, "median": 39.74, "p90": 41.95, "p95": 43.51, "mean": 40.26 }, "e2e_ms": { "n": 1000, "median": 44.46, "p90": 48.63, "p95": 51.13, "mean": 45.34 }, "forward_ms_by_candidates": { "1-5": { "n": 102, "median": 39.66, "p90": 41.49, "p95": 42.07, "mean": 39.85 }, "6-10": { "n": 171, "median": 39.49, "p90": 41.12, "p95": 42.08, "mean": 39.72 }, "11-20": { "n": 406, "median": 39.62, "p90": 40.93, "p95": 41.55, "mean": 39.71 }, "21-50": { "n": 295, "median": 40.27, "p90": 42.85, "p95": 43.91, "mean": 40.47 }, ">50": { "n": 21, "median": 48.97, "p90": 69.71, "p95": 78.59, "mean": 54.25 } }, "forward_ms_by_input_tokens": { "<=512": { "n": 649, "median": 39.6, "p90": 41.14, "p95": 41.81, "mean": 39.78 }, "513-1024": { "n": 292, "median": 39.85, "p90": 41.68, "p95": 42.49, "mean": 39.92 }, "1025-1536": { "n": 49, "median": 42.88, "p90": 46.74, "p95": 48.44, "mean": 43.75 }, ">1536": { "n": 10, "median": 53.1, "p90": 83.47, "p95": 105.45, "mean": 64.05 } }, "peak_vram_allocated_gb_bs1": 1.66, "peak_vram_reserved_gb_bs1": 1.91, "batch_sweep": { "1": { "batch_ms": { "n": 1000, "median": 39.06, "p90": 41.12, "p95": 42.26, "mean": 39.48 }, "throughput_steps_per_s": 25.3, "peak_vram_allocated_gb": 1.66, "peak_vram_reserved_gb": 1.91 }, "4": { "batch_ms": { "n": 250, "median": 39.99, "p90": 51.89, "p95": 67.4, "mean": 44.25 }, "throughput_steps_per_s": 90.4, "peak_vram_allocated_gb": 2.3, "peak_vram_reserved_gb": 3.45 }, "8": { "batch_ms": { "n": 125, "median": 71.35, "p90": 134.79, "p95": 158.07, "mean": 81.02 }, "throughput_steps_per_s": 98.7, "peak_vram_allocated_gb": 3.16, "peak_vram_reserved_gb": 6.3 }, "16": { "batch_ms": { "n": 63, "median": 177.91, "p90": 293.32, "p95": 371.29, "mean": 198.02 }, "throughput_steps_per_s": 80.2, "peak_vram_allocated_gb": 4.89, "peak_vram_reserved_gb": 11.99 }, "32": { "batch_ms": { "n": 32, "median": 431.11, "p90": 778.52, "p95": 827.76, "mean": 535.89 }, "throughput_steps_per_s": 58.3, "peak_vram_allocated_gb": 8.34, "peak_vram_reserved_gb": 23.35 } }, "params_m": 321.9 } } }