## single stream (ms)
ab-af32    b1_3    n=120 e2e p50 39.3 [38.2,40.3] p90 42.1 p99 62.1 max 71.4 | server p50 37.7 p90 40.3 p99 59.0 | http overhead p50 1.6
ab-af32    b3_8    n=120 e2e p50 47.8 [47.1,49.0] p90 54.5 p99 59.5 max 72.8 | server p50 46.2 p90 52.4 p99 57.5 | http overhead p50 1.7
ab-af32    b8_20   n=120 e2e p50 68.3 [66.7,71.9] p90 81.4 p99 87.2 max 88.5 | server p50 66.2 p90 79.2 p99 84.9 | http overhead p50 2.1
ab-af32    b20_60  n=120 e2e p50 170.0 [160.5,177.9] p90 223.8 p99 239.2 max 242.1 | server p50 165.0 p90 217.6 p99 233.0 | http overhead p50 5.1
ab-b16     b1_3    n=120 e2e p50 28.5 [28.2,28.8] p90 31.4 p99 58.3 max 70.4 | server p50 27.2 p90 30.0 p99 55.1 | http overhead p50 1.3
ab-b16     b3_8    n=120 e2e p50 32.2 [31.8,33.0] p90 35.5 p99 40.6 max 64.7 | server p50 30.8 p90 34.0 p99 38.9 | http overhead p50 1.4
ab-b16     b8_20   n=120 e2e p50 38.4 [37.9,39.2] p90 43.2 p99 45.8 max 71.2 | server p50 36.6 p90 41.2 p99 44.1 | http overhead p50 1.7
ab-b16     b20_60  n=120 e2e p50 65.7 [62.9,70.3] p90 82.1 p99 302.1 max 454.3 | server p50 61.9 p90 76.7 p99 91.8 | http overhead p50 3.8
ab-b16w    b1_3    n=120 e2e p50 23.0 [22.7,23.2] p90 26.1 p99 50.9 max 60.4 | server p50 21.8 p90 24.9 p99 47.5 | http overhead p50 1.3
ab-b16w    b3_8    n=120 e2e p50 27.0 [26.6,27.9] p90 30.3 p99 43.2 max 63.7 | server p50 25.7 p90 29.0 p99 41.1 | http overhead p50 1.4
ab-b16w    b8_20   n=120 e2e p50 33.2 [32.5,34.1] p90 38.2 p99 207.1 max 240.5 | server p50 31.5 p90 36.2 p99 42.9 | http overhead p50 1.6
ab-b16w    b20_60  n=120 e2e p50 61.8 [59.2,68.1] p90 77.4 p99 268.9 max 442.5 | server p50 57.5 p90 72.6 p99 98.4 | http overhead p50 4.4
ab-b32     b1_3    n=120 e2e p50 22.6 [22.3,23.0] p90 24.3 p99 33.1 max 46.6 | server p50 21.4 p90 23.1 p99 29.9 | http overhead p50 1.2
ab-b32     b3_8    n=120 e2e p50 26.3 [25.7,26.8] p90 28.8 p99 31.2 max 57.9 | server p50 25.0 p90 27.4 p99 29.8 | http overhead p50 1.3
ab-b32     b8_20   n=120 e2e p50 34.0 [33.1,34.9] p90 40.1 p99 44.6 max 65.4 | server p50 32.4 p90 38.3 p99 42.6 | http overhead p50 1.6
ab-b32     b20_60  n=120 e2e p50 76.1 [71.8,85.4] p90 98.3 p99 306.8 max 408.1 | server p50 72.2 p90 93.1 p99 97.4 | http overhead p50 4.0
ab-b32c    b1_3    n=120 e2e p50 22.7 [22.5,23.1] p90 25.0 p99 49.3 max 55.9 | server p50 21.4 p90 23.5 p99 46.0 | http overhead p50 1.3
ab-b32c    b3_8    n=120 e2e p50 26.3 [25.9,26.6] p90 28.9 p99 37.5 max 56.4 | server p50 24.8 p90 27.4 p99 35.8 | http overhead p50 1.4
ab-b32c    b8_20   n=120 e2e p50 33.9 [32.8,34.6] p90 40.0 p99 44.2 max 62.5 | server p50 32.3 p90 38.0 p99 42.4 | http overhead p50 1.7
ab-b32c    b20_60  n=120 e2e p50 77.9 [72.4,85.1] p90 98.7 p99 273.7 max 422.6 | server p50 73.2 p90 93.4 p99 101.1 | http overhead p50 4.4
ab-cf32    b1_3    n=120 e2e p50 40.6 [39.9,41.6] p90 43.7 p99 63.8 max 73.2 | server p50 39.1 p90 42.1 p99 60.3 | http overhead p50 1.6
ab-cf32    b3_8    n=120 e2e p50 51.2 [49.9,52.0] p90 59.5 p99 67.5 max 74.0 | server p50 49.5 p90 57.7 p99 65.4 | http overhead p50 1.8
ab-cf32    b8_20   n=120 e2e p50 75.5 [73.4,80.5] p90 92.0 p99 99.0 max 99.2 | server p50 73.2 p90 89.6 p99 96.7 | http overhead p50 2.1
ab-cf32    b20_60  n=120 e2e p50 190.2 [177.9,206.0] p90 254.5 p99 264.7 max 266.5 | server p50 185.1 p90 248.5 p99 258.2 | http overhead p50 5.2

## paired median difference vs ab-b32 (e2e ms; 95% bootstrap CI)
ab-af32    b1_3    pairs=120 diff    +16.5 [   +15.4,   +17.0]
ab-af32    b3_8    pairs=120 diff    +21.6 [   +20.9,   +22.3]
ab-af32    b8_20   pairs=120 diff    +35.0 [   +33.4,   +36.6]
ab-af32    b20_60  pairs=120 diff    +92.2 [   +83.5,   +98.1]
ab-b16     b1_3    pairs=120 diff     +5.8 [    +5.7,    +6.0]
ab-b16     b3_8    pairs=120 diff     +6.0 [    +5.7,    +6.4]
ab-b16     b8_20   pairs=120 diff     +4.7 [    +4.5,    +5.3]
ab-b16     b20_60  pairs=120 diff     -9.7 [   -11.5,    -8.1]
ab-b16w    b1_3    pairs=120 diff     +0.5 [    +0.4,    +0.6]
ab-b16w    b3_8    pairs=120 diff     +0.9 [    +0.4,    +1.2]
ab-b16w    b8_20   pairs=120 diff     -0.3 [    -0.8,    +0.3]
ab-b16w    b20_60  pairs=120 diff    -13.7 [   -15.2,   -12.2]
ab-b32c    b1_3    pairs=120 diff     +0.0 [    -0.0,    +0.1]
ab-b32c    b3_8    pairs=120 diff     +0.1 [    -0.0,    +0.1]
ab-b32c    b8_20   pairs=120 diff     -0.1 [    -0.1,    -0.1]
ab-b32c    b20_60  pairs=120 diff     +1.2 [    +0.9,    +1.5]
ab-cf32    b1_3    pairs=120 diff    +18.1 [   +17.4,   +18.5]
ab-cf32    b3_8    pairs=120 diff    +24.8 [   +23.9,   +25.8]
ab-cf32    b8_20   pairs=120 diff    +42.3 [   +40.1,   +45.4]
ab-cf32    b20_60  pairs=120 diff   +111.0 [  +104.0,  +120.0]

## concurrency 4 (ms)
ab-af32    b1_3    n=40 err=0 e2e p50 144.1 p90 157.4 p99 174.4 | server p50 37.3 | 26.94 req/s, 60.2x realtime
ab-af32    b20_60  n=40 err=0 e2e p50 684.2 p90 1047.8 p99 1200.8 | server p50 167.9 | 5.64 req/s, 242.3x realtime
ab-af32    b3_8    n=40 err=0 e2e p50 187.4 p90 226.0 p99 269.7 | server p50 46.2 | 21.13 req/s, 105.2x realtime
ab-af32    b8_20   n=40 err=0 e2e p50 273.4 p90 292.1 p99 354.1 | server p50 65.7 | 14.56 req/s, 174.6x realtime
ab-b16     b1_3    n=40 err=0 e2e p50 105.2 p90 107.3 p99 132.3 | server p50 25.7 | 36.53 req/s, 81.7x realtime
ab-b16     b20_60  n=40 err=0 e2e p50 258.1 p90 393.5 p99 528.4 | server p50 60.9 | 15.13 req/s, 649.5x realtime
ab-b16     b3_8    n=40 err=0 e2e p50 117.5 p90 145.5 p99 170.1 | server p50 29.3 | 33.28 req/s, 165.6x realtime
ab-b16     b8_20   n=40 err=0 e2e p50 145.2 p90 153.3 p99 182.5 | server p50 35.5 | 27.29 req/s, 327.1x realtime
ab-b16w    b1_3    n=40 err=0 e2e p50 84.4 p90 86.1 p99 114.2 | server p50 20.6 | 45.25 req/s, 101.2x realtime
ab-b16w    b20_60  n=40 err=0 e2e p50 236.2 p90 370.4 p99 443.2 | server p50 55.3 | 16.52 req/s, 709.0x realtime
ab-b16w    b3_8    n=40 err=0 e2e p50 97.2 p90 122.1 p99 140.4 | server p50 23.9 | 40.32 req/s, 200.7x realtime
ab-b16w    b8_20   n=40 err=0 e2e p50 124.3 p90 130.7 p99 156.6 | server p50 30.5 | 31.8 req/s, 381.2x realtime
ab-b32     b1_3    n=40 err=0 e2e p50 83.8 p90 88.4 p99 107.7 | server p50 20.4 | 45.61 req/s, 102.0x realtime
ab-b32     b20_60  n=40 err=0 e2e p50 314.2 p90 455.5 p99 490.8 | server p50 71.8 | 13.02 req/s, 558.8x realtime
ab-b32     b3_8    n=40 err=0 e2e p50 96.8 p90 118.8 p99 139.3 | server p50 24.1 | 40.53 req/s, 201.7x realtime
ab-b32     b8_20   n=40 err=0 e2e p50 129.4 p90 147.6 p99 166.6 | server p50 31.1 | 30.46 req/s, 365.2x realtime
ab-b32c    b1_3    n=40 err=0 e2e p50 86.1 p90 88.5 p99 112.7 | server p50 20.9 | 44.44 req/s, 99.4x realtime
ab-b32c    b20_60  n=40 err=0 e2e p50 302.8 p90 453.7 p99 556.9 | server p50 71.0 | 13.11 req/s, 563.0x realtime
ab-b32c    b3_8    n=40 err=0 e2e p50 96.4 p90 116.4 p99 207.8 | server p50 24.3 | 40.36 req/s, 200.9x realtime
ab-b32c    b8_20   n=40 err=0 e2e p50 129.5 p90 148.6 p99 164.9 | server p50 30.9 | 30.7 req/s, 368.1x realtime
ab-cf32    b1_3    n=40 err=0 e2e p50 148.5 p90 162.5 p99 180.1 | server p50 38.8 | 26.04 req/s, 58.2x realtime
ab-cf32    b20_60  n=40 err=0 e2e p50 789.2 p90 1167.6 p99 1283.0 | server p50 188.9 | 5.09 req/s, 218.6x realtime
ab-cf32    b3_8    n=40 err=0 e2e p50 199.3 p90 255.9 p99 284.7 | server p50 48.8 | 19.98 req/s, 99.4x realtime
ab-cf32    b8_20   n=40 err=0 e2e p50 295.0 p90 329.7 p99 369.9 | server p50 72.3 | 13.26 req/s, 159.0x realtime

## first call per bin after cold start (ms) vs that arm's warm e2e p50
ab-b32     b1_3    first     59.9  warm p50 22.6
ab-b32     b3_8    first     43.8  warm p50 26.3
ab-b32     b8_20   first     37.8  warm p50 34.0
ab-b32     b20_60  first    418.2  warm p50 76.1
ab-b32c    b1_3    first     59.5  warm p50 22.7
ab-b32c    b3_8    first     41.6  warm p50 26.3
ab-b32c    b8_20   first     37.5  warm p50 33.9
ab-b32c    b20_60  first    402.2  warm p50 77.9
ab-b16w    b1_3    first     63.8  warm p50 23.0
ab-b16w    b3_8    first     30.0  warm p50 27.0
ab-b16w    b8_20   first     35.5  warm p50 33.2
ab-b16w    b20_60  first    425.7  warm p50 61.8
ab-b16     b1_3    first     66.9  warm p50 28.5
ab-b16     b3_8    first     34.6  warm p50 32.2
ab-b16     b8_20   first     45.7  warm p50 38.4
ab-b16     b20_60  first    371.1  warm p50 65.7
ab-cf32    b1_3    first     82.2  warm p50 40.6
ab-cf32    b3_8    first     52.0  warm p50 51.2
ab-cf32    b8_20   first     76.1  warm p50 75.5
ab-cf32    b20_60  first    254.3  warm p50 190.2
ab-af32    b1_3    first     80.1  warm p50 39.3
ab-af32    b3_8    first     55.0  warm p50 47.8
ab-af32    b8_20   first     71.4  warm p50 68.3
ab-af32    b20_60  first    226.0  warm p50 170.0

## GPU memory per process (MiB)
{"arm": "ab-b32", "pid": 3296542, "cold_s": 11.8, "rest_after_warmup_mib": 3836, "peak_utterance_block_mib": 4800, "peak_whole_life_mib": 5620, "last_mib": 4800, "samples": 2211}
{"arm": "ab-b32c", "pid": 3298073, "cold_s": 12.1, "rest_after_warmup_mib": 3836, "peak_utterance_block_mib": 4800, "peak_whole_life_mib": 4800, "last_mib": 4800, "samples": 2108}
{"arm": "ab-b16w", "pid": 3299497, "cold_s": 13.0, "rest_after_warmup_mib": 2492, "peak_utterance_block_mib": 2794, "peak_whole_life_mib": 3194, "last_mib": 2794, "samples": 2006}
{"arm": "ab-b16", "pid": 3301181, "cold_s": 11.8, "rest_after_warmup_mib": 4802, "peak_utterance_block_mib": 5126, "peak_whole_life_mib": 5620, "last_mib": 5126, "samples": 1892}
{"arm": "ab-cf32", "pid": 3302918, "cold_s": 45.2, "rest_after_warmup_mib": 3874, "peak_utterance_block_mib": 6946, "peak_whole_life_mib": 6946, "last_mib": 6946, "samples": 1789}
{"arm": "ab-af32", "pid": 3306068, "cold_s": 44.7, "rest_after_warmup_mib": 3922, "peak_utterance_block_mib": 6994, "peak_whole_life_mib": 6994, "last_mib": 6994, "samples": 1494}
