[ { "decode_tps_ratio": 0.6129207541251469, "e2e_p50_ratio": 0.7394530533987747, "e2e_p95_ratio": 1.2287231205931113, "fixture": "coder_100", "frontier_complete": false, "frontier_completed": 96, "frontier_decode_tps": 347.79923381681954, "frontier_e2e_p50_s": 30.939283157873398, "frontier_e2e_p95_s": 119.6361375789676, "frontier_preemptions": 0, "frontier_prefix_hit": 0.24878456156190046, "frontier_rps": 0.4048148795016268, "frontier_total": 100, "frontier_total_tps": 2348.908820556559, "frontier_tpot_p50_s": 0.056889664283438265, "frontier_tpot_p95_s": 0.14568807925543142, "frontier_ttft_p50_s": 0.9087481136376141, "frontier_ttft_p95_s": 12.762958146117297, "kv_blocks": 15281, "label": "TP1 N100 raw", "notes": "Frontier incomplete before lifecycle fix; included as TP1 100-request baseline.", "prefix_hit_delta": -0.0022975070751777016, "request_count": 100, "rps_ratio": 0.5884039239601411, "run_id": "tp1_n100_scale1", "scale_label": "raw", "scale_value": 1.0, "total_tps_ratio": 0.6129207541251469, "tp": 1, "tpot_p50_ratio": 0.8609035602986401, "tpot_p95_ratio": 0.23454605053898236, "ttft_p50_ratio": 0.20180834300191677, "ttft_p95_ratio": 0.439186240241972, "vllm_completed": 100, "vllm_decode_tps": 567.445679520595, "vllm_e2e_p50_s": 41.84076732886024, "vllm_e2e_p95_s": 97.36622968502343, "vllm_preemptions": 8, "vllm_prefix_hit": 0.25108206863707816, "vllm_rps": 0.6879880691092217, "vllm_total": 100, "vllm_total_tps": 3832.3205810011714, "vllm_tpot_p50_s": 0.06608134395878643, "vllm_tpot_p95_s": 0.6211491471318447, "vllm_ttft_p50_s": 4.503025494981557, "vllm_ttft_p95_s": 29.060469059972093 }, { "decode_tps_ratio": 0.8960505440100501, "e2e_p50_ratio": 0.7927945162118318, "e2e_p95_ratio": 0.951923946910999, "fixture": "coder_500", "frontier_complete": false, "frontier_completed": 439, "frontier_decode_tps": 656.2204997652797, "frontier_e2e_p50_s": 177.7998574092898, "frontier_e2e_p95_s": 397.29145000151055, "frontier_preemptions": 0, "frontier_prefix_hit": 0.11923746923408568, "frontier_rps": 0.6609904720097601, "frontier_total": 500, "frontier_total_tps": 4733.748762075876, "frontier_tpot_p50_s": 0.05643274739314083, "frontier_tpot_p95_s": 0.08942839772817235, "frontier_ttft_p50_s": 136.77557892500107, "frontier_ttft_p95_s": 340.237122196321, "kv_blocks": 15281, "label": "TP1 N500 raw", "notes": "Frontier incomplete; useful as high-pressure stress signal.", "prefix_hit_delta": -0.2676124002320734, "request_count": 500, "rps_ratio": 0.786732377640824, "run_id": "tp1_n500_scale1", "scale_label": "raw", "scale_value": 1.0, "total_tps_ratio": 0.8960505440100502, "tp": 1, "tpot_p50_ratio": 1.134268756171416, "tpot_p95_ratio": 0.9733188934802052, "ttft_p50_ratio": 0.736706497600023, "ttft_p95_ratio": 0.9051387119015346, "vllm_completed": 500, "vllm_decode_tps": 732.3476383692921, "vllm_e2e_p50_s": 224.26978715602309, "vllm_e2e_p95_s": 417.3562933159992, "vllm_preemptions": 63, "vllm_prefix_hit": 0.38684986946615907, "vllm_rps": 0.8401719451179492, "vllm_total": 500, "vllm_total_tps": 5282.903730956031, "vllm_tpot_p50_s": 0.049752536236317216, "vllm_tpot_p95_s": 0.09187985389702198, "vllm_ttft_p50_s": 185.6581683079712, "vllm_ttft_p95_s": 375.8950067239348 }, { "decode_tps_ratio": 0.8044430383408974, "e2e_p50_ratio": 0.8754552629577944, "e2e_p95_ratio": 1.030008185534932, "fixture": "coder_200_ts0667", "frontier_complete": false, "frontier_completed": 176, "frontier_decode_tps": 593.287826008356, "frontier_e2e_p50_s": 73.20731168652793, "frontier_e2e_p95_s": 189.24029025053343, "frontier_preemptions": 0, "frontier_prefix_hit": 0.17027600800712456, "frontier_rps": 0.5830903705506575, "frontier_total": 200, "frontier_total_tps": 3913.43752605849, "frontier_tpot_p50_s": 0.05837096651496554, "frontier_tpot_p95_s": 0.23589456903741046, "frontier_ttft_p50_s": 20.58014532403832, "frontier_ttft_p95_s": 96.7179381828816, "kv_blocks": 15281, "label": "TP1 N200 scale 0.667", "notes": "Dense-arrival run; Frontier incomplete before lifecycle fix.", "prefix_hit_delta": -0.09947893983522305, "request_count": 200, "rps_ratio": 0.7079098737399896, "run_id": "tp1_n200_scale0667", "scale_label": "0.667", "scale_value": 0.6666666666666666, "total_tps_ratio": 0.8044430383408974, "tp": 1, "tpot_p50_ratio": 1.1344230703885074, "tpot_p95_ratio": 0.930639595403931, "ttft_p50_ratio": 0.5954345540217358, "ttft_p95_ratio": 0.800618794003408, "vllm_completed": 200, "vllm_decode_tps": 737.5137800085473, "vllm_e2e_p50_s": 83.62199050490744, "vllm_e2e_p95_s": 183.7269770358689, "vllm_preemptions": 26, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 0.8236788215286605, "vllm_total": 200, "vllm_total_tps": 4864.778908559713, "vllm_tpot_p50_s": 0.051454318973762715, "vllm_tpot_p95_s": 0.2534757495838373, "vllm_ttft_p50_s": 34.563236522022635, "vllm_ttft_p95_s": 120.80398175423034 }, { "decode_tps_ratio": 0.7393232177681209, "e2e_p50_ratio": 1.1173620884379967, "e2e_p95_ratio": 1.2258475306262637, "fixture": "coder_200_ts2", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 531.5597035900641, "frontier_e2e_p50_s": 61.45769412455945, "frontier_e2e_p95_s": 174.48408358603848, "frontier_preemptions": 33, "frontier_prefix_hit": 0.23134168999974056, "frontier_rps": 0.5936627654877362, "frontier_total": 200, "frontier_total_tps": 3506.267279013048, "frontier_tpot_p50_s": 0.054213625462090735, "frontier_tpot_p95_s": 0.06653162646338621, "frontier_ttft_p50_s": 9.595321273711544, "frontier_ttft_p95_s": 77.50341053197451, "kv_blocks": 15281, "label": "TP1 N200 scale 2", "notes": "After Frontier decode-preemption lifecycle fix.", "prefix_hit_delta": -0.038413257842607046, "request_count": 200, "rps_ratio": 0.7393232177681209, "run_id": "tp1_n200_scale2", "scale_label": "2", "scale_value": 2.0, "total_tps_ratio": 0.7393232177681209, "tp": 1, "tpot_p50_ratio": 1.0907433399899442, "tpot_p95_ratio": 0.9693811149298648, "ttft_p50_ratio": 1.0410723384685256, "ttft_p95_ratio": 1.1198067467817787, "vllm_completed": 200, "vllm_decode_tps": 718.9814830849542, "vllm_e2e_p50_s": 55.002487340942025, "vllm_e2e_p95_s": 142.3375087250024, "vllm_preemptions": 43, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 0.8029813635231063, "vllm_total": 200, "vllm_total_tps": 4742.53640998563, "vllm_tpot_p50_s": 0.049703375188695206, "vllm_tpot_p95_s": 0.06863309532102842, "vllm_ttft_p50_s": 9.216767095960677, "vllm_ttft_p95_s": 69.2114159471821 }, { "decode_tps_ratio": 0.7356557719569122, "e2e_p50_ratio": 1.3476957295017153, "e2e_p95_ratio": 1.258652459348984, "fixture": "coder_200_ts3", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 513.9343093668691, "frontier_e2e_p50_s": 44.76058145123308, "frontier_e2e_p95_s": 154.54831351855702, "frontier_preemptions": 20, "frontier_prefix_hit": 0.21767512777477313, "frontier_rps": 0.573978165231764, "frontier_total": 200, "frontier_total_tps": 3390.0068803652352, "frontier_tpot_p50_s": 0.053393334371887605, "frontier_tpot_p95_s": 0.06861254670772189, "frontier_ttft_p50_s": 1.0014741156186515, "frontier_ttft_p95_s": 45.94665669959886, "kv_blocks": 15281, "label": "TP1 N200 scale 3", "notes": "After Frontier decode-preemption lifecycle fix.", "prefix_hit_delta": -0.05207982006757447, "request_count": 200, "rps_ratio": 0.7356557719569123, "run_id": "tp1_n200_scale3", "scale_label": "3", "scale_value": 3.0, "total_tps_ratio": 0.7356557719569123, "tp": 1, "tpot_p50_ratio": 1.1566613307426805, "tpot_p95_ratio": 0.9611804148017213, "ttft_p50_ratio": 0.8587856162345445, "ttft_p95_ratio": 1.4243304641052532, "vllm_completed": 200, "vllm_decode_tps": 698.607050957755, "vllm_e2e_p50_s": 33.2126758818049, "vllm_e2e_p95_s": 122.78871134808287, "vllm_preemptions": 16, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 0.7802265503945264, "vllm_total": 200, "vllm_total_tps": 4608.1428428781355, "vllm_tpot_p50_s": 0.04616159713544178, "vllm_tpot_p95_s": 0.07138362959869063, "vllm_ttft_p50_s": 1.1661514779552817, "vllm_ttft_p95_s": 32.25842447206378 }, { "decode_tps_ratio": 0.6070363250137228, "e2e_p50_ratio": 1.5837949050918096, "e2e_p95_ratio": 1.4718353941122981, "fixture": "coder_200_ts2", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 694.538225813865, "frontier_e2e_p50_s": 26.05122481685102, "frontier_e2e_p95_s": 106.75916510714146, "frontier_preemptions": 0, "frontier_prefix_hit": 0.2697549478423476, "frontier_rps": 0.7756823572006221, "frontier_total": 200, "frontier_total_tps": 4581.304110804026, "frontier_tpot_p50_s": 0.042955276577521156, "frontier_tpot_p95_s": 0.05288764732371923, "frontier_ttft_p50_s": 0.2690959621493789, "frontier_ttft_p95_s": 6.744624223172184, "kv_blocks": 69055, "label": "TP2 N200 scale 2", "notes": "Uses true-mixed TP2/TP4 attention profile.", "prefix_hit_delta": 0.0, "request_count": 200, "rps_ratio": 0.6070363250137228, "run_id": "tp2_n200_scale2", "scale_label": "2", "scale_value": 2.0, "total_tps_ratio": 0.6070363250137228, "tp": 2, "tpot_p50_ratio": 1.4296981582601855, "tpot_p95_ratio": 1.218502045500008, "ttft_p50_ratio": 1.1953492307083635, "ttft_p95_ratio": 9.432094021900193, "vllm_completed": 200, "vllm_decode_tps": 1144.1460703330465, "vllm_e2e_p50_s": 16.448610065039247, "vllm_e2e_p95_s": 72.53471789998002, "vllm_preemptions": 0, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 1.2778186827338327, "vllm_total": 200, "vllm_total_tps": 7547.001591215254, "vllm_tpot_p50_s": 0.030044996791346416, "vllm_tpot_p95_s": 0.043403823177019754, "vllm_ttft_p50_s": 0.22511911601759493, "vllm_ttft_p95_s": 0.7150717759504914 }, { "decode_tps_ratio": 0.6321128225155744, "e2e_p50_ratio": 2.1882239414176055, "e2e_p95_ratio": 1.8819058641979227, "fixture": "coder_200_ts3", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 615.822856748031, "frontier_e2e_p50_s": 21.785964943721574, "frontier_e2e_p95_s": 101.59183927019191, "frontier_preemptions": 0, "frontier_prefix_hit": 0.2697549478423476, "frontier_rps": 0.6877705321122985, "frontier_total": 200, "frontier_total_tps": 4062.0828059403734, "frontier_tpot_p50_s": 0.0393789684875167, "frontier_tpot_p95_s": 0.04670767224504207, "frontier_ttft_p50_s": 0.13415354950526392, "frontier_ttft_p95_s": 0.574137821753455, "kv_blocks": 69055, "label": "TP2 N200 scale 3", "notes": "Uses true-mixed TP2/TP4 attention profile.", "prefix_hit_delta": 0.0, "request_count": 200, "rps_ratio": 0.6321128225155745, "run_id": "tp2_n200_scale3", "scale_label": "3", "scale_value": 3.0, "total_tps_ratio": 0.6321128225155745, "tp": 2, "tpot_p50_ratio": 2.066305230245682, "tpot_p95_ratio": 1.668678182045304, "ttft_p50_ratio": 0.8737883511042303, "ttft_p95_ratio": 0.9156237864420547, "vllm_completed": 200, "vllm_decode_tps": 974.229338201501, "vllm_e2e_p50_s": 9.956003373954445, "vllm_e2e_p95_s": 53.98348621092737, "vllm_preemptions": 0, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 1.0880502777577379, "vllm_total": 200, "vllm_total_tps": 6426.199028481642, "vllm_tpot_p50_s": 0.01905767256023186, "vllm_tpot_p95_s": 0.02799082096692385, "vllm_ttft_p50_s": 0.15353094297461212, "vllm_ttft_p95_s": 0.6270455510821193 }, { "decode_tps_ratio": 0.554961482872708, "e2e_p50_ratio": 2.0140798462106178, "e2e_p95_ratio": 1.9471360828275543, "fixture": "coder_200_ts2", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 763.3502329676248, "frontier_e2e_p50_s": 18.65216281946347, "frontier_e2e_p95_s": 84.93775413567799, "frontier_preemptions": 0, "frontier_prefix_hit": 0.2697549478423476, "frontier_rps": 0.8525337930595883, "frontier_total": 200, "frontier_total_tps": 5035.200987216818, "frontier_tpot_p50_s": 0.03366585046876145, "frontier_tpot_p95_s": 0.03838265621202119, "frontier_ttft_p50_s": 0.09755515041058871, "frontier_ttft_p95_s": 0.3856872342439675, "kv_blocks": 177077, "label": "TP4 N200 scale 2", "notes": "Uses true-mixed TP2/TP4 attention profile.", "prefix_hit_delta": 0.0, "request_count": 200, "rps_ratio": 0.5549614828727081, "run_id": "tp4_n200_scale2", "scale_label": "2", "scale_value": 2.0, "total_tps_ratio": 0.5549614828727081, "tp": 4, "tpot_p50_ratio": 2.0597817670263323, "tpot_p95_ratio": 1.3554681431066735, "ttft_p50_ratio": 0.5721801588631308, "ttft_p95_ratio": 0.27163724014492546, "vllm_completed": 200, "vllm_decode_tps": 1375.5012852715674, "vllm_e2e_p50_s": 9.26088548800908, "vllm_e2e_p95_s": 43.621889032190666, "vllm_preemptions": 0, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 1.5362035373095158, "vllm_total": 200, "vllm_total_tps": 9073.06388391597, "vllm_tpot_p50_s": 0.016344377354773947, "vllm_tpot_p95_s": 0.02831690025857032, "vllm_ttft_p50_s": 0.1704972619190812, "vllm_ttft_p95_s": 1.4198614079505205 }, { "decode_tps_ratio": 0.5882440161960838, "e2e_p50_ratio": 3.045852424279607, "e2e_p95_ratio": 2.9785685814353515, "fixture": "coder_200_ts3", "frontier_complete": true, "frontier_completed": 200, "frontier_decode_tps": 660.2306058712501, "frontier_e2e_p50_s": 16.902919407154563, "frontier_e2e_p95_s": 83.00995364867583, "frontier_preemptions": 0, "frontier_prefix_hit": 0.2697549478423476, "frontier_rps": 0.7373665172396945, "frontier_total": 200, "frontier_total_tps": 4355.004629460394, "frontier_tpot_p50_s": 0.031067781092248118, "frontier_tpot_p95_s": 0.035782850818878296, "frontier_ttft_p50_s": 0.08859749134958328, "frontier_ttft_p95_s": 0.3458954617429286, "kv_blocks": 177077, "label": "TP4 N200 scale 3", "notes": "Uses true-mixed TP2/TP4 attention profile.", "prefix_hit_delta": 0.0, "request_count": 200, "rps_ratio": 0.5882440161960838, "run_id": "tp4_n200_scale3", "scale_label": "3", "scale_value": 3.0, "total_tps_ratio": 0.5882440161960839, "tp": 4, "tpot_p50_ratio": 3.301471070786272, "tpot_p95_ratio": 2.7971158799197804, "ttft_p50_ratio": 0.8850343170011207, "ttft_p95_ratio": 1.086290918512101, "vllm_completed": 200, "vllm_decode_tps": 1122.3753879226379, "vllm_e2e_p50_s": 5.549487320007756, "vllm_e2e_p95_s": 27.869075825903565, "vllm_preemptions": 0, "vllm_prefix_hit": 0.2697549478423476, "vllm_rps": 1.2535044929278167, "vllm_total": 200, "vllm_total_tps": 7403.398095950554, "vllm_tpot_p50_s": 0.00941028421153152, "vllm_tpot_p95_s": 0.01279276667647553, "vllm_ttft_p50_s": 0.1001062779687345, "vllm_ttft_p95_s": 0.3184188101440668 } ]