| Dataset | Run | Req | Output tok/s | Speedup | Latency mean/p95 ms | TTFT mean/p95 ms | ITL mean/p95 ms | TPOT mean/p95 ms | Accept rate | Accept p1/p2/p3 | Accept len | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | math500 | baseline | 500 | 266.74 | 1.000x | 1901.95/2310.23 | 211.01/379.08 | 13.40/16.31 | 13.40/16.31 | — | -/-/- | — | | math500 | dflash_k3 | 500 | 185.18 | 0.694x | 2740.52/3396.06 | 232.73/422.78 | 19.89/24.71 | 19.90/24.71 | 6.29% | 16.64%/1.97%/0.24% | 1.189 | | math500 | dflash_k7 | 500 | 188.44 | 0.706x | 2690.23/3411.27 | 223.15/410.68 | 19.61/24.83 | 19.61/24.83 | 2.74% | 16.86%/2.02%/0.26% | 1.192 | | math500 | dflare_k3 | 500 | 217.77 | 0.816x | 2328.94/3331.75 | 279.51/506.23 | 16.27/23.21 | 16.27/23.21 | 39.35% | 64.89%/35.28%/17.89% | 2.181 | | math500 | dflare_k7 | 500 | 225.99 | 0.847x | 2249.20/3338.34 | 263.03/475.01 | 15.76/24.25 | 15.76/24.25 | 18.69% | 64.67%/35.48%/17.53% | 2.309 | | math500 | dspark_k3 | 500 | 286.34 | 1.073x | 1774.14/2512.93 | 237.01/434.45 | 12.18/17.88 | 12.18/17.88 | 44.99% | 65.67%/42.25%/27.05% | 2.350 | | math500 | dspark_k7 | 500 | 294.75 | 1.105x | 1725.25/2646.27 | 247.76/461.03 | 11.72/18.88 | 11.72/18.88 | 22.89% | 63.98%/39.64%/24.22% | 2.602 | | gsm8k | baseline | 1319 | 280.58 | 1.000x | 1819.24/2167.76 | 217.05/398.45 | 12.64/15.22 | 12.64/15.22 | — | -/-/- | — | | gsm8k | dflash_k3 | 1319 | 188.79 | 0.673x | 2702.38/3317.10 | 235.61/424.62 | 19.48/24.18 | 19.48/24.19 | 6.81% | 18.37%/1.86%/0.20% | 1.204 | | gsm8k | dflash_k7 | 1319 | 188.46 | 0.672x | 2705.30/3477.26 | 301.18/834.45 | 18.98/23.59 | 18.98/23.59 | 2.74% | 17.14%/1.81%/0.20% | 1.192 | | gsm8k | dflare_k3 | 1319 | 201.03 | 0.716x | 2536.44/3534.03 | 258.19/484.66 | 17.98/25.82 | 17.98/25.82 | 27.95% | 53.64%/21.51%/8.69% | 1.838 | | gsm8k | dflare_k7 | 1319 | 154.41 | 0.550x | 3304.27/5885.10 | 1205.81/4089.58 | 16.56/27.05 | 16.56/27.06 | 12.83% | 54.22%/21.89%/9.37% | 1.898 | | gsm8k | dspark_k3 | 1319 | 267.82 | 0.954x | 1904.86/2717.59 | 232.41/436.56 | 13.20/19.22 | 13.20/19.23 | 31.15% | 53.33%/25.75%/14.35% | 1.934 | | gsm8k | dspark_k7 | 1319 | 256.27 | 0.913x | 1991.49/2946.94 | 240.23/457.41 | 13.82/21.07 | 13.82/21.07 | 14.63% | 53.19%/24.90%/13.31% | 2.024 | | humaneval | baseline | 164 | 194.21 | 1.000x | 1403.54/2734.28 | 218.21/420.29 | 17.84/29.90 | 17.85/29.91 | — | -/-/- | — | | humaneval | dflash_k3 | 164 | 147.26 | 0.758x | 1856.84/3610.00 | 250.89/497.85 | 24.55/42.01 | 24.56/42.02 | 5.95% | 16.41%/1.35%/0.08% | 1.179 | | humaneval | dflash_k7 | 164 | 141.91 | 0.731x | 1877.28/3978.09 | 343.90/982.06 | 22.96/33.21 | 22.97/33.23 | 2.68% | 17.40%/1.31%/0.09% | 1.188 | | humaneval | dflare_k3 | 164 | 194.56 | 1.002x | 1401.65/2758.01 | 307.73/627.48 | 17.78/33.04 | 17.78/33.05 | 58.74% | 77.35%/56.42%/42.44% | 2.762 | | humaneval | dflare_k7 | 164 | 206.56 | 1.064x | 1296.23/2684.54 | 395.19/956.47 | 16.23/32.95 | 16.23/32.96 | 33.05% | 77.91%/56.44%/40.45% | 3.313 | | humaneval | dspark_k3 | 164 | 234.79 | 1.209x | 1172.97/2107.93 | 265.30/502.88 | 14.78/29.63 | 14.78/29.64 | 59.91% | 76.53%/58.74%/44.47% | 2.797 | | humaneval | dspark_k7 | 164 | 210.60 | 1.084x | 1276.63/2616.22 | 564.26/1681.50 | 12.49/25.28 | 12.49/25.28 | 35.09% | 74.01%/55.03%/39.85% | 3.457 | | mbpp | baseline | 500 | 275.24 | 1.000x | 1788.02/2216.35 | 221.07/398.67 | 13.20/15.66 | 13.21/15.67 | — | -/-/- | — | | mbpp | dflash_k3 | 500 | 189.94 | 0.690x | 2595.66/3320.97 | 234.11/439.53 | 19.14/23.96 | 19.15/23.96 | 6.46% | 18.25%/1.11%/0.04% | 1.194 | | mbpp | dflash_k7 | 500 | 170.29 | 0.619x | 2875.58/4074.32 | 634.04/1885.92 | 18.20/24.69 | 18.21/24.70 | 2.85% | 18.78%/1.13%/0.05% | 1.200 | | mbpp | dflare_k3 | 500 | 244.12 | 0.887x | 2016.51/2791.48 | 280.07/557.88 | 14.26/19.44 | 14.27/19.63 | 47.05% | 68.89%/44.50%/27.76% | 2.411 | | mbpp | dflare_k7 | 500 | 184.84 | 0.672x | 2657.85/4488.95 | 1190.47/3259.46 | 12.45/22.86 | 12.46/22.86 | 24.66% | 67.13%/42.74%/25.45% | 2.726 | | mbpp | dspark_k3 | 500 | 310.80 | 1.129x | 1592.68/2178.77 | 240.73/455.66 | 11.35/15.68 | 11.35/15.68 | 52.29% | 71.25%/50.82%/34.79% | 2.569 | | mbpp | dspark_k7 | 500 | 274.50 | 0.997x | 1794.33/3171.44 | 643.14/2119.01 | 10.10/14.88 | 10.11/14.88 | 28.83% | 68.32%/47.02%/30.55% | 3.018 | | mt_bench | baseline | 160 | 309.23 | 1.000x | 1607.62/2284.11 | 320.49/629.17 | 11.01/15.18 | 11.01/15.19 | — | -/-/- | — | | mt_bench | dflash_k3 | 160 | 195.62 | 0.633x | 2573.23/3166.33 | 221.35/448.16 | 18.68/23.10 | 18.68/23.11 | 6.07% | 16.45%/1.71%/0.06% | 1.182 | | mt_bench | dflash_k7 | 160 | 180.37 | 0.583x | 2753.90/3791.87 | 381.83/1026.59 | 21.71/25.58 | 21.71/25.58 | 2.48% | 15.47%/1.60%/0.12% | 1.173 | | mt_bench | dflare_k3 | 160 | 225.31 | 0.729x | 2231.25/3333.71 | 248.97/520.00 | 15.78/23.60 | 15.78/23.60 | 32.30% | 57.50%/27.57%/11.81% | 1.969 | | mt_bench | dflare_k7 | 160 | 133.91 | 0.433x | 3752.53/6717.97 | 1934.01/4820.78 | 14.32/29.83 | 14.32/29.83 | 14.58% | 56.90%/26.94%/11.54% | 2.021 | | mt_bench | dspark_k3 | 160 | 282.93 | 0.915x | 1771.67/2604.84 | 252.12/503.80 | 12.36/19.15 | 12.36/19.15 | 36.54% | 58.03%/32.54%/19.06% | 2.096 | | mt_bench | dspark_k7 | 160 | 224.25 | 0.725x | 2225.17/3657.94 | 838.84/2441.89 | 11.43/22.87 | 11.43/23.00 | 17.22% | 55.30%/29.97%/16.74% | 2.205 | | ultrachat | baseline | 5000 | 155.46 | 1.000x | 3269.57/3934.88 | 231.24/386.99 | 24.09/28.91 | 24.09/28.91 | — | -/-/- | — | | ultrachat | dflash_k3 | 5000 | 135.15 | 0.869x | 3763.95/4515.90 | 257.60/405.56 | 27.76/33.28 | 27.77/33.28 | 7.09% | 18.40%/2.57%/0.30% | 1.213 | | ultrachat | dflash_k7 | 5000 | 134.03 | 0.862x | 3794.92/4543.27 | 255.94/399.63 | 28.03/33.56 | 28.03/33.56 | 3.07% | 18.54%/2.58%/0.31% | 1.215 | | ultrachat | dflare_k3 | 5000 | 161.25 | 1.037x | 3155.82/4013.42 | 282.90/456.06 | 22.75/29.20 | 22.75/29.20 | 31.06% | 57.10%/26.00%/10.07% | 1.932 | | ultrachat | dflare_k7 | 5000 | 157.88 | 1.016x | 3221.08/4123.29 | 352.64/612.31 | 22.73/29.63 | 22.73/29.63 | 14.37% | 57.63%/26.59%/10.33% | 2.006 | | ultrachat | dspark_k3 | 5000 | 190.92 | 1.228x | 2665.16/3441.95 | 264.37/429.11 | 19.01/24.80 | 19.01/24.80 | 32.40% | 55.58%/28.18%/13.44% | 1.972 | | ultrachat | dspark_k7 | 5000 | 189.60 | 1.220x | 2683.34/3469.80 | 287.66/433.69 | 18.97/25.07 | 18.97/25.07 | 15.40% | 55.21%/27.94%/13.27% | 2.078 |