[ { "baseline": "outputs/gpu_ab_combined", "e2e_p50_delta_pct": 40.870329127661, "e2e_p90_delta_pct": 15.206416995091814, "error_count": [ 2, 13 ], "gpu_imbalance_ratio": [ 3.2445157838416265, 11.149056603773586 ], "gpu_mean_util": [ 30.541666666666664, 12.367081447963802 ], "name": "combined_vs_pdsep_200", "request_count": [ 200, 200 ], "success_count": [ 198, 187 ], "tpot_p90_delta_pct": 1.3481309269699875, "ttft_p50_delta_pct": 98.06752892925572, "ttft_p90_delta_pct": 44.79649177751278, "variant": "outputs/gpu_ab_pdsep", "wall_clock_delta_pct": 142.27736808267244 }, { "baseline": "outputs/contention_16s_ts10", "e2e_p50_delta_pct": 11.538788125232664, "e2e_p90_delta_pct": -5.080083318118138, "error_count": [ 2, 2 ], "gpu_imbalance_ratio": [ 2.310775410408662, 2.600767754318618 ], "gpu_mean_util": [ 23.030492424242425, 26.349561403508773 ], "name": "contention_baseline_vs_elastic_500", "request_count": [ 500, 500 ], "success_count": [ 498, 498 ], "tpot_p90_delta_pct": 13.63098996823875, "ttft_p50_delta_pct": 12.433589435386224, "ttft_p90_delta_pct": 13.412576920999959, "variant": "outputs/contention_16s_elastic", "wall_clock_delta_pct": -0.5645626396767849 }, { "baseline": "outputs/combined_1000req", "e2e_p50_delta_pct": 202.85189980479385, "e2e_p90_delta_pct": 128.274511020719, "error_count": [ 2, 204 ], "gpu_imbalance_ratio": [ null, null ], "gpu_mean_util": [ null, null ], "name": "combined_1000_vs_pdsep_mooncake", "request_count": [ 1000, 1000 ], "success_count": [ 998, 796 ], "tpot_p90_delta_pct": -34.83638659447109, "ttft_p50_delta_pct": 781.9835547522864, "ttft_p90_delta_pct": 1030.68607857992, "variant": "outputs/exp3_pd_sep_tp1_mooncake", "wall_clock_delta_pct": 119.18997774599991 } ]