[ { "apc_summary": { "reason": "apc.txt missing", "status": "unavailable" }, "artifact_availability": { "apc_txt": false, "breakdown_json": false, "gpu_util_csv": true, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "reason": "breakdown.json missing", "status": "unavailable" }, "error_count": 2, "exists": true, "external_cache_hit_ratio": null, "gpu_summary": { "gpu_count": 8, "max_mean_util_pct": 63.166666666666664, "max_min_ratio": 3.2445157838416265, "mean_util_pct": 30.541666666666664, "min_mean_util_pct": 19.46875, "per_gpu_mean_util_pct": { "0": 29.145833333333332, "1": 20.041666666666668, "2": 25.0, "3": 63.166666666666664, "4": 21.927083333333332, "5": 34.90625, "6": 19.46875, "7": 30.677083333333332 }, "status": "available", "stddev_across_gpu_mean_util_pct": 13.337857305429534 }, "latency_stats_s": { "count": 198.0, "mean": 13.01780862723021, "p50": 5.048548387829214, "p90": 30.18109704903327, "p99": 119.01174414204434 }, "metrics_jsonl_rows": 200, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.0, "request_count": 200, "run": "outputs/gpu_ab_combined", "session_summary": { "request_cached_tokens": { "count": 200, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 200, "max": 111927.0, "mean": 29318.375, "p50": 21376.0, "p90": 81218.19999999998, "p95": 87571.2, "p99": 101619.27999999994 }, "request_output_tokens": { "count": 200, "max": 5083.0, "mean": 257.675, "p50": 72.0, "p90": 664.3, "p95": 1063.9999999999993, "p99": 3300.1799999999994 }, "session_count": 145, "session_input_tokens": { "count": 145, "max": 1567423.0, "mean": 40439.137931034486, "p50": 10879.0, "p90": 72438.39999999997, "p95": 106934.39999999988, "p99": 374927.28 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6588294883328288, "top_1pct": 0.33276622595897626, "top_5pct": 0.5534430199490934 }, "turns_per_session": { "count": 145, "max": 21.0, "mean": 1.3793103448275863, "p50": 1.0, "p90": 1.0, "p95": 2.0, "p99": 10.560000000000002 } }, "success_count": 198, "tpot_stats_s": { "count": 198.0, "mean": 0.04929455188644857, "p50": 0.03717198147904128, "p90": 0.07317714408040046, "p99": 0.10039294634234945 }, "ttft_stats_s": { "count": 198.0, "mean": 3.8987488178453984, "p50": 1.0068706551101059, "p90": 9.355209570843726, "p99": 33.855437273858115 }, "wall_clock_s": 483.543720243033 }, { "apc_summary": { "reason": "apc.txt missing", "status": "unavailable" }, "artifact_availability": { "apc_txt": false, "breakdown_json": false, "gpu_util_csv": true, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "reason": "breakdown.json missing", "status": "unavailable" }, "error_count": 13, "exists": true, "external_cache_hit_ratio": null, "gpu_summary": { "gpu_count": 8, "max_mean_util_pct": 26.737556561085974, "max_min_ratio": 11.149056603773586, "mean_util_pct": 12.367081447963802, "min_mean_util_pct": 2.3981900452488687, "per_gpu_mean_util_pct": { "0": 26.737556561085974, "1": 14.44343891402715, "2": 19.036199095022624, "3": 7.4389140271493215, "4": 2.3981900452488687, "5": 8.841628959276019, "6": 11.963800904977376, "7": 8.076923076923077 }, "status": "available", "stddev_across_gpu_mean_util_pct": 7.15857427072345 }, "latency_stats_s": { "count": 187.0, "mean": 15.366858840781827, "p50": 7.111906730104238, "p90": 34.77056052000262, "p99": 119.2064151619561 }, "metrics_jsonl_rows": 200, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.0, "request_count": 200, "run": "outputs/gpu_ab_pdsep", "session_summary": { "request_cached_tokens": { "count": 200, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 200, "max": 111927.0, "mean": 29318.375, "p50": 21376.0, "p90": 81218.19999999998, "p95": 87571.2, "p99": 101619.27999999994 }, "request_output_tokens": { "count": 200, "max": 5097.0, "mean": 290.18, "p50": 75.5, "p90": 685.8, "p95": 1102.5999999999997, "p99": 3433.6599999999844 }, "session_count": 145, "session_input_tokens": { "count": 145, "max": 1567423.0, "mean": 40439.137931034486, "p50": 10879.0, "p90": 72438.39999999997, "p95": 106934.39999999988, "p99": 374927.28 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6588294883328288, "top_1pct": 0.33276622595897626, "top_5pct": 0.5534430199490934 }, "turns_per_session": { "count": 145, "max": 21.0, "mean": 1.3793103448275863, "p50": 1.0, "p90": 1.0, "p95": 2.0, "p99": 10.560000000000002 } }, "success_count": 187, "tpot_stats_s": { "count": 187.0, "mean": 0.05175559044923285, "p50": 0.04020531923068981, "p90": 0.07416366779122173, "p99": 0.10770365060609463 }, "ttft_stats_s": { "count": 187.0, "mean": 5.3933139261814524, "p50": 1.9942838260903955, "p90": 13.546015257015824, "p99": 39.30951087013818 }, "wall_clock_s": 1171.516998933861 }, { "apc_summary": { "reason": "apc.txt missing", "status": "unavailable" }, "artifact_availability": { "apc_txt": false, "breakdown_json": false, "gpu_util_csv": true, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "reason": "breakdown.json missing", "status": "unavailable" }, "error_count": 2, "exists": true, "external_cache_hit_ratio": 0.0, "gpu_summary": { "gpu_count": 8, "max_mean_util_pct": 40.095454545454544, "max_min_ratio": 2.310775410408662, "mean_util_pct": 23.030492424242425, "min_mean_util_pct": 17.35151515151515, "per_gpu_mean_util_pct": { "0": 22.243939393939392, "1": 22.798484848484847, "2": 22.09090909090909, "3": 40.095454545454544, "4": 17.484848484848484, "5": 20.225757575757576, "6": 17.35151515151515, "7": 21.953030303030303 }, "status": "available", "stddev_across_gpu_mean_util_pct": 6.752783259358802 }, "latency_stats_s": { "count": 498.0, "mean": 21.908606036002105, "p50": 5.798741589998826, "p90": 51.00022796400299, "p99": 201.6967467680006 }, "metrics_jsonl_rows": 500, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.0, "request_count": 500, "run": "outputs/contention_16s_ts10", "session_summary": { "request_cached_tokens": { "count": 500, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 500, "max": 134865.0, "mean": 29190.97, "p50": 17756.0, "p90": 77365.70000000006, "p95": 87790.89999999997, "p99": 111360.44 }, "request_output_tokens": { "count": 500, "max": 16427.0, "mean": 404.286, "p50": 75.0, "p90": 863.7000000000004, "p95": 2384.45, "p99": 4928.559999999999 }, "session_count": 347, "session_input_tokens": { "count": 347, "max": 1929072.0, "mean": 42061.916426512966, "p50": 11342.0, "p90": 68297.20000000004, "p95": 116213.79999999993, "p99": 521898.36000000057 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6824335059780473, "top_1pct": 0.32352388426969025, "top_5pct": 0.579125805000656 }, "turns_per_session": { "count": 347, "max": 29.0, "mean": 1.440922190201729, "p50": 1.0, "p90": 1.0, "p95": 3.0, "p99": 10.54000000000002 } }, "success_count": 498, "tpot_stats_s": { "count": 498.0, "mean": 0.07772806444638436, "p50": 0.06774563665097065, "p90": 0.10325221968416468, "p99": 0.503443661631568 }, "ttft_stats_s": { "count": 498.0, "mean": 3.5127640336366928, "p50": 0.8264882279981975, "p90": 9.71474659699743, "p99": 34.40133859900379 }, "wall_clock_s": 1472.1331836190002 }, { "apc_summary": { "line_count": 8, "preview": "inst_0: prefix=45.7% ext=24.7%\ninst_1: prefix=33.1% ext=13.3%\ninst_2: prefix=14.2% ext=0.0%\ninst_3: prefix=50.7% ext=6.3%\ninst_4: prefix=33.6% ext=0.0%\ninst_5: prefix=66.6% ext=9.2%\ninst_6: prefix=42.1% ext=18.8%\ninst_7: prefix=36.7% ext=7.9%", "status": "available" }, "artifact_availability": { "apc_txt": true, "breakdown_json": true, "gpu_util_csv": true, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "field_sample": [ "cache_hit", "estimated_new_tokens", "input_length", "policy", "request_id", "route_class", "routed_to", "t_done", "t_first_token", "t_proxy_recv" ], "mode_counts": { "HEAVY_COLO": 111, "HEAVY_OFFLOAD": 13, "MEDIUM": 163, "WARM": 213 }, "route_counts": { "linear": 487 }, "row_count": 500, "status": "available" }, "error_count": 2, "exists": true, "external_cache_hit_ratio": 0.0, "gpu_summary": { "gpu_count": 8, "max_mean_util_pct": 47.54385964912281, "max_min_ratio": 2.600767754318618, "mean_util_pct": 26.349561403508773, "min_mean_util_pct": 18.280701754385966, "per_gpu_mean_util_pct": { "0": 22.410526315789475, "1": 26.57894736842105, "2": 23.54035087719298, "3": 47.54385964912281, "4": 18.96842105263158, "5": 26.403508771929825, "6": 18.280701754385966, "7": 27.07017543859649 }, "status": "available", "stddev_across_gpu_mean_util_pct": 8.6079068381278 }, "latency_stats_s": { "count": 498.0, "mean": 21.780466573040204, "p50": 6.467846095998539, "p90": 48.40937389100145, "p99": 196.93401125499804 }, "metrics_jsonl_rows": 500, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.0, "request_count": 500, "run": "outputs/contention_16s_elastic", "session_summary": { "request_cached_tokens": { "count": 500, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 500, "max": 134865.0, "mean": 29190.97, "p50": 17756.0, "p90": 77365.70000000006, "p95": 87790.89999999997, "p99": 111360.44 }, "request_output_tokens": { "count": 500, "max": 16427.0, "mean": 395.466, "p50": 75.0, "p90": 809.8000000000013, "p95": 2264.2999999999943, "p99": 4928.559999999999 }, "session_count": 347, "session_input_tokens": { "count": 347, "max": 1929072.0, "mean": 42061.916426512966, "p50": 11342.0, "p90": 68297.20000000004, "p95": 116213.79999999993, "p99": 521898.36000000057 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6824335059780473, "top_1pct": 0.32352388426969025, "top_5pct": 0.579125805000656 }, "turns_per_session": { "count": 347, "max": 29.0, "mean": 1.440922190201729, "p50": 1.0, "p90": 1.0, "p95": 3.0, "p99": 10.54000000000002 } }, "success_count": 498, "tpot_stats_s": { "count": 498.0, "mean": 0.08306021258238128, "p50": 0.06973490711122092, "p90": 0.117326519391297, "p99": 0.5879216773072795 }, "ttft_stats_s": { "count": 498.0, "mean": 3.757858794331448, "p50": 0.9292503809992922, "p90": 11.017744456999935, "p99": 34.20241540799907 }, "wall_clock_s": 1463.8220696580029 }, { "apc_summary": { "reason": "apc.txt missing", "status": "unavailable" }, "artifact_availability": { "apc_txt": false, "breakdown_json": false, "gpu_util_csv": false, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "reason": "breakdown.json missing", "status": "unavailable" }, "error_count": 2, "exists": true, "external_cache_hit_ratio": null, "gpu_summary": { "reason": "gpu_util.csv missing", "status": "unavailable" }, "latency_stats_s": { "count": 998.0, "mean": 15.744418202954922, "p50": 3.220371481962502, "p90": 28.005282410187647, "p99": 204.00479479599744 }, "metrics_jsonl_rows": 1000, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.5443149471989938, "request_count": 1000, "run": "outputs/combined_1000req", "session_summary": { "request_cached_tokens": { "count": 1000, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 1000, "max": 171427.0, "mean": 31611.14, "p50": 19798.0, "p90": 82584.20000000001, "p95": 93305.64999999997, "p99": 111947.83999999998 }, "request_output_tokens": { "count": 1000, "max": 41233.0, "mean": 392.579, "p50": 70.0, "p90": 685.8000000000002, "p95": 1834.6999999999975, "p99": 4584.459999999996 }, "session_count": 671, "session_input_tokens": { "count": 671, "max": 2320064.0, "mean": 47110.49180327869, "p50": 12394.0, "p90": 71875.0, "p95": 112984.5, "p99": 760591.4999999925 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6915149849072194, "top_1pct": 0.36223103627392117, "top_5pct": 0.5945521736957288 }, "turns_per_session": { "count": 671, "max": 36.0, "mean": 1.4903129657228018, "p50": 1.0, "p90": 1.0, "p95": 3.0, "p99": 12.599999999999909 } }, "success_count": 998, "tpot_stats_s": { "count": 998.0, "mean": 0.05681003092240363, "p50": 0.04029440155459775, "p90": 0.11343103184021618, "p99": 0.2962149563411783 }, "ttft_stats_s": { "count": 998.0, "mean": 1.0351265607308877, "p50": 0.39304836583323777, "p90": 2.5655168020166457, "p99": 8.210839052917436 }, "wall_clock_s": 1340.061015482992 }, { "apc_summary": { "reason": "apc.txt missing", "status": "unavailable" }, "artifact_availability": { "apc_txt": false, "breakdown_json": false, "gpu_util_csv": false, "metrics_jsonl": true, "metrics_summary_json": true }, "breakdown_summary": { "reason": "breakdown.json missing", "status": "unavailable" }, "error_count": 204, "exists": true, "external_cache_hit_ratio": null, "gpu_summary": { "reason": "gpu_util.csv missing", "status": "unavailable" }, "latency_stats_s": { "count": 796.0, "mean": 23.561836449842698, "p50": 9.752956213895231, "p90": 63.928921481827274, "p99": 168.2179710320197 }, "metrics_jsonl_rows": 1000, "metrics_summary_available": true, "prefix_cache_hit_ratio": 0.0, "request_count": 1000, "run": "outputs/exp3_pd_sep_tp1_mooncake", "session_summary": { "request_cached_tokens": { "count": 1000, "max": 0.0, "mean": 0.0, "p50": 0.0, "p90": 0.0, "p95": 0.0, "p99": 0.0 }, "request_input_tokens": { "count": 1000, "max": 171427.0, "mean": 31611.14, "p50": 19798.0, "p90": 82584.20000000001, "p95": 93305.64999999997, "p99": 111947.83999999998 }, "request_output_tokens": { "count": 1000, "max": 41233.0, "mean": 412.176, "p50": 74.0, "p90": 759.7000000000008, "p95": 1834.6999999999975, "p99": 4928.559999999999 }, "session_count": 671, "session_input_tokens": { "count": 671, "max": 2320064.0, "mean": 47110.49180327869, "p50": 12394.0, "p90": 71875.0, "p95": 112984.5, "p99": 760591.4999999925 }, "status": "available", "top_session_input_fraction": { "top_10pct": 0.6915149849072194, "top_1pct": 0.36223103627392117, "top_5pct": 0.5945521736957288 }, "turns_per_session": { "count": 671, "max": 36.0, "mean": 1.4903129657228018, "p50": 1.0, "p90": 1.0, "p95": 3.0, "p99": 12.599999999999909 } }, "success_count": 796, "tpot_stats_s": { "count": 796.0, "mean": 0.05211825330315642, "p50": 0.06622354774330945, "p90": 0.07391575907026088, "p99": 0.10499966285609896 }, "ttft_stats_s": { "count": 796.0, "mean": 10.753033336598003, "p50": 3.4666219488717616, "p90": 29.00794132403098, "p99": 81.7531874559354 }, "wall_clock_s": 2937.2794416199904 } ]