Created
July 24, 2026 02:18
-
-
Save nateraw/5ac359374bf2810770f1a57d891f9794 to your computer and use it in GitHub Desktop.
poolside/Laguna-S-2.1-NVFP4 - Single DGX Spark Benchmark
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| MODEL_NAME="poolside/Laguna-S-2.1-NVFP4" | |
| source .venv/bin/activate | |
| uvx llama-benchy \ | |
| --base-url http://localhost:8000/v1 \ | |
| --model "$MODEL_NAME" \ | |
| --depth 0 4096 8192 16384 32768 65535 100000 \ | |
| --pp 2048 \ | |
| --tg 128 \ | |
| --enable-prefix-caching \ | |
| --concurrency 1 2 5 10 \ | |
| --save-result results.csv |
We can make this file beautiful and searchable if this error is corrected: No commas found in this CSV file in line 0.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| | model | test | t/s (total) | t/s (req) | peak t/s | peak t/s (req) | ttfr (ms) | est_ppt (ms) | e2e_ttft (ms) | | |
| |:----------------------------|-----------------------:|----------------:|-----------------:|---------------:|-----------------:|----------------------:|----------------------:|----------------------:| | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 (c1) | 1945.70 ± 60.45 | 1945.70 ± 60.45 | | | 1056.97 ± 33.48 | 1054.13 ± 33.48 | 1056.97 ± 33.48 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 (c1) | 19.36 ± 1.26 | 19.36 ± 1.26 | 27.00 ± 0.82 | 27.00 ± 0.82 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 (c2) | 2329.02 ± 7.96 | 1216.94 ± 50.62 | | | 1689.35 ± 70.03 | 1686.50 ± 70.03 | 1689.35 ± 70.03 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 (c2) | 28.18 ± 1.03 | 14.94 ± 0.93 | 44.67 ± 4.99 | 24.83 ± 5.15 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 (c5) | 2450.62 ± 0.54 | 740.19 ± 243.54 | | | 3063.41 ± 915.36 | 3060.56 ± 915.36 | 3063.41 ± 915.36 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 (c5) | 40.37 ± 0.65 | 9.98 ± 0.77 | 64.33 ± 2.87 | 18.33 ± 2.80 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 (c10) | 2430.47 ± 15.71 | 504.94 ± 278.17 | | | 5174.88 ± 2202.03 | 5172.04 ± 2202.03 | 5174.88 ± 2202.03 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 (c10) | 56.24 ± 0.24 | 7.62 ± 0.86 | 110.33 ± 5.79 | 17.30 ± 3.20 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d4096 (c1) | 2349.14 ± 20.23 | 2349.14 ± 20.23 | | | 1747.44 ± 15.11 | 1744.60 ± 15.11 | 1747.44 ± 15.11 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d4096 (c1) | 18.27 ± 1.57 | 18.27 ± 1.57 | 25.67 ± 0.47 | 25.67 ± 0.47 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d4096 (c1) | 1890.05 ± 8.41 | 1890.05 ± 8.41 | | | 1086.43 ± 4.81 | 1083.59 ± 4.81 | 1086.43 ± 4.81 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d4096 (c1) | 19.81 ± 1.22 | 19.81 ± 1.22 | 28.67 ± 3.40 | 28.67 ± 3.40 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d4096 (c2) | 2390.08 ± 4.94 | 1458.15 ± 262.03 | | | 2906.94 ± 521.99 | 2904.09 ± 521.99 | 2906.94 ± 521.99 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d4096 (c2) | 27.94 ± 0.90 | 15.58 ± 0.90 | 46.67 ± 2.05 | 26.17 ± 2.91 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d4096 (c2) | 2223.66 ± 12.55 | 1159.39 ± 46.24 | | | 1772.11 ± 70.58 | 1769.26 ± 70.58 | 1772.11 ± 70.58 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d4096 (c2) | 28.04 ± 0.55 | 15.73 ± 2.74 | 53.33 ± 11.67 | 31.17 ± 11.61 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d4096 (c5) | 2478.80 ± 2.71 | 904.38 ± 439.60 | | | 5487.02 ± 2095.09 | 5484.17 ± 2095.09 | 5487.02 ± 2095.09 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d4096 (c5) | 32.77 ± 1.87 | 9.35 ± 1.44 | 74.00 ± 9.42 | 19.07 ± 2.67 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d4096 (c5) | 2309.26 ± 36.34 | 699.87 ± 232.33 | | | 3244.94 ± 979.54 | 3242.10 ± 979.54 | 3244.94 ± 979.54 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d4096 (c5) | 40.08 ± 0.31 | 9.98 ± 0.93 | 70.67 ± 1.89 | 18.67 ± 3.96 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d4096 (c10) | 2467.57 ± 8.63 | 598.20 ± 426.67 | | | 9661.02 ± 4578.95 | 9658.18 ± 4578.95 | 9661.02 ± 4578.95 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d4096 (c10) | 41.35 ± 1.76 | 7.29 ± 2.18 | 118.67 ± 13.30 | 19.23 ± 8.29 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d4096 (c10) | 2291.77 ± 19.65 | 479.92 ± 266.18 | | | 5479.33 ± 2385.31 | 5476.49 ± 2385.31 | 5479.33 ± 2385.31 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d4096 (c10) | 54.45 ± 2.34 | 7.35 ± 1.21 | 107.33 ± 11.03 | 16.70 ± 5.37 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d8192 (c1) | 2390.39 ± 6.89 | 2390.39 ± 6.89 | | | 3430.49 ± 10.21 | 3427.65 ± 10.21 | 3430.49 ± 10.21 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d8192 (c1) | 18.21 ± 0.29 | 18.21 ± 0.29 | 26.67 ± 0.47 | 26.67 ± 0.47 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d8192 (c1) | 1800.56 ± 4.20 | 1800.56 ± 4.20 | | | 1140.27 ± 2.65 | 1137.43 ± 2.65 | 1140.27 ± 2.65 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d8192 (c1) | 20.44 ± 1.21 | 20.44 ± 1.21 | 29.67 ± 1.70 | 29.67 ± 1.70 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d8192 (c2) | 2473.18 ± 11.04 | 1579.81 ± 342.89 | | | 5445.71 ± 1180.86 | 5442.86 ± 1180.86 | 5445.71 ± 1180.86 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d8192 (c2) | 19.06 ± 1.65 | 12.11 ± 1.85 | 34.67 ± 1.70 | 19.67 ± 2.36 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d8192 (c2) | 2140.89 ± 1.93 | 1114.24 ± 42.11 | | | 1843.50 ± 69.56 | 1840.65 ± 69.56 | 1843.50 ± 69.56 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d8192 (c2) | 26.75 ± 2.20 | 14.19 ± 1.13 | 41.00 ± 2.16 | 23.33 ± 3.59 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d8192 (c5) | 2481.85 ± 12.88 | 986.81 ± 514.75 | | | 10407.21 ± 4342.41 | 10404.36 ± 4342.41 | 10407.21 ± 4342.41 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d8192 (c5) | 23.43 ± 1.72 | 7.91 ± 1.84 | 60.67 ± 2.62 | 17.60 ± 3.18 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d8192 (c5) | 2222.17 ± 24.44 | 671.61 ± 220.21 | | | 3374.91 ± 1012.26 | 3372.06 ± 1012.26 | 3374.91 ± 1012.26 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d8192 (c5) | 39.28 ± 0.49 | 9.49 ± 0.75 | 66.33 ± 0.47 | 19.60 ± 3.98 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d8192 (c10) | 2439.96 ± 5.92 | 647.10 ± 497.76 | | | 18774.07 ± 9413.99 | 18771.22 ± 9413.99 | 18774.07 ± 9413.99 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d8192 (c10) | 27.69 ± 0.53 | 6.32 ± 3.67 | 109.67 ± 13.89 | 16.63 ± 10.03 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d8192 (c10) | 2231.90 ± 2.34 | 468.46 ± 261.65 | | | 5627.13 ± 2453.91 | 5624.29 ± 2453.91 | 5627.13 ± 2453.91 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d8192 (c10) | 54.37 ± 0.90 | 7.35 ± 1.04 | 111.33 ± 7.32 | 17.37 ± 6.04 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d16384 (c1) | 2409.56 ± 1.00 | 2409.56 ± 1.00 | | | 6802.98 ± 2.88 | 6800.14 ± 2.88 | 6802.98 ± 2.88 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d16384 (c1) | 18.18 ± 0.87 | 18.18 ± 0.87 | 24.33 ± 2.05 | 24.33 ± 2.05 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d16384 (c1) | 1687.19 ± 8.75 | 1687.19 ± 8.75 | | | 1216.73 ± 6.29 | 1213.89 ± 6.29 | 1216.73 ± 6.29 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d16384 (c1) | 16.50 ± 0.26 | 16.50 ± 0.26 | 25.00 ± 2.16 | 25.00 ± 2.16 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d16384 (c2) | 2443.46 ± 8.94 | 1683.55 ± 461.71 | | | 10527.14 ± 2885.56 | 10524.30 ± 2885.56 | 10527.14 ± 2885.56 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d16384 (c2) | 18.35 ± 1.14 | 13.05 ± 4.00 | 48.67 ± 15.06 | 28.67 ± 12.83 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d16384 (c2) | 1991.75 ± 5.01 | 1032.52 ± 34.83 | | | 1988.60 ± 66.99 | 1985.75 ± 66.99 | 1989.24 ± 67.10 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d16384 (c2) | 22.69 ± 1.50 | 12.30 ± 1.35 | 32.00 ± 3.74 | 17.83 ± 1.86 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d16384 (c5) | 2418.98 ± 2.36 | 1033.76 ± 601.31 | | | 20820.35 ± 9318.98 | 20817.51 ± 9318.98 | 20820.79 ± 9319.35 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d16384 (c5) | 16.41 ± 0.48 | 7.76 ± 3.51 | 52.67 ± 3.09 | 17.73 ± 5.64 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d16384 (c5) | 2085.98 ± 2.21 | 629.32 ± 206.37 | | | 3601.05 ± 1078.22 | 3598.20 ± 1078.22 | 3601.15 ± 1078.34 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d16384 (c5) | 36.65 ± 1.43 | 9.62 ± 1.99 | 75.00 ± 12.25 | 19.93 ± 7.05 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d16384 (c10) | 2381.14 ± 9.13 | 672.86 ± 568.31 | | | 38057.28 ± 19691.16 | 38054.43 ± 19691.16 | 38057.68 ± 19691.17 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d16384 (c10) | 16.35 ± 1.46 | 4.98 ± 2.71 | 57.33 ± 11.84 | 13.14 ± 5.15 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d16384 (c10) | 2054.52 ± 11.89 | 428.23 ± 236.76 | | | 6128.38 ± 2656.39 | 6125.54 ± 2656.39 | 6129.08 ± 2656.64 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d16384 (c10) | 48.83 ± 2.64 | 6.87 ± 1.23 | 105.67 ± 13.89 | 16.17 ± 5.63 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d32768 (c1) | 2294.24 ± 9.52 | 2294.24 ± 9.52 | | | 14286.53 ± 59.36 | 14283.68 ± 59.36 | 14290.19 ± 59.30 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d32768 (c1) | 20.56 ± 0.71 | 20.56 ± 0.71 | 29.33 ± 1.89 | 29.33 ± 1.89 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d32768 (c1) | 1474.15 ± 1.04 | 1474.15 ± 1.04 | | | 1392.12 ± 0.98 | 1389.27 ± 0.98 | 1394.84 ± 2.90 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d32768 (c1) | 19.17 ± 1.78 | 19.17 ± 1.78 | 27.00 ± 2.94 | 27.00 ± 2.94 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d32768 (c2) | 2280.21 ± 1.42 | 1661.95 ± 521.63 | | | 21875.08 ± 6864.50 | 21872.23 ± 6864.50 | 21877.59 ± 6865.00 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d32768 (c2) | 10.82 ± 0.08 | 9.73 ± 3.32 | 31.67 ± 0.94 | 21.50 ± 2.06 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d32768 (c2) | 1700.59 ± 44.25 | 879.32 ± 36.19 | | | 2335.90 ± 96.62 | 2333.05 ± 96.62 | 2338.32 ± 95.34 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d32768 (c2) | 25.50 ± 0.88 | 13.04 ± 0.43 | 35.00 ± 2.83 | 19.50 ± 0.96 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d32768 (c5) | 2259.59 ± 1.93 | 1011.76 ± 629.83 | | | 43894.06 ± 20398.26 | 43891.21 ± 20398.26 | 43896.07 ± 20398.41 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d32768 (c5) | 9.04 ± 0.09 | 5.64 ± 3.49 | 37.67 ± 2.36 | 15.80 ± 6.33 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d32768 (c5) | 1822.73 ± 2.63 | 547.13 ± 178.12 | | | 4135.82 ± 1230.42 | 4132.97 ± 1230.42 | 4136.14 ± 1230.07 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d32768 (c5) | 34.91 ± 1.81 | 9.05 ± 2.17 | 67.00 ± 8.04 | 18.67 ± 5.94 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d32768 (c10) | 2252.99 ± 7.41 | 651.12 ± 574.36 | | | 80270.31 ± 41751.87 | 80267.47 ± 41751.87 | 80271.02 ± 41750.93 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d32768 (c10) | 8.23 ± 0.53 | 4.58 ± 3.68 | 42.33 ± 6.60 | 12.49 ± 7.40 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d32768 (c10) | 455.12 ± 238.33 | 118.96 ± 174.51 | | | 30984.92 ± 16000.73 | 30982.07 ± 16000.73 | 30985.14 ± 16000.34 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d32768 (c10) | 22.79 ± 5.08 | 4.77 ± 2.41 | 73.67 ± 5.73 | 12.87 ± 3.76 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d65535 (c1) | 2036.61 ± 0.98 | 2036.61 ± 0.98 | | | 32182.35 ± 15.54 | 32179.51 ± 15.54 | 32182.35 ± 15.54 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d65535 (c1) | 21.13 ± 1.99 | 21.13 ± 1.99 | 30.00 ± 4.32 | 30.00 ± 4.32 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d65535 (c1) | 1183.18 ± 3.51 | 1183.18 ± 3.51 | | | 1733.79 ± 5.13 | 1730.94 ± 5.13 | 1737.68 ± 7.33 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d65535 (c1) | 16.96 ± 2.21 | 16.96 ± 2.21 | 26.33 ± 1.25 | 26.33 ± 1.25 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d65535 (c2) | 2008.88 ± 2.54 | 1503.95 ± 499.46 | | | 48980.98 ± 16265.70 | 48978.14 ± 16265.70 | 48982.83 ± 16263.85 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d65535 (c2) | 6.04 ± 0.29 | 10.41 ± 6.87 | 31.33 ± 7.13 | 22.17 ± 5.87 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d65535 (c2) | 1387.00 ± 5.14 | 711.54 ± 17.34 | | | 2882.82 ± 70.16 | 2879.98 ± 70.16 | 2882.82 ± 70.16 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d65535 (c2) | 25.88 ± 2.21 | 14.67 ± 1.79 | 40.67 ± 6.65 | 23.67 ± 2.92 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d65535 (c5) | 1994.69 ± 4.54 | 910.49 ± 581.61 | | | 98801.62 ± 46555.04 | 98798.78 ± 46555.04 | 98803.51 ± 46554.61 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d65535 (c5) | 3.94 ± 0.25 | 5.22 ± 4.75 | 26.00 ± 7.12 | 10.73 ± 5.56 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d65535 (c5) | 1441.78 ± 1.70 | 428.58 ± 137.47 | | | 5263.36 ± 1542.75 | 5260.52 ± 1542.75 | 5263.69 ± 1542.40 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d65535 (c5) | 30.75 ± 0.82 | 7.63 ± 0.94 | 54.33 ± 3.40 | 15.27 ± 1.98 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d65535 (c10) | 1981.39 ± 1.49 | 581.71 ± 525.55 | | | 182102.92 ± 95193.75 | 182100.08 ± 95193.75 | 182103.67 ± 95192.89 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d65535 (c10) | 3.81 ± 0.02 | 3.80 ± 3.34 | 32.00 ± 4.24 | 10.81 ± 6.23 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d65535 (c10) | 66.15 ± 5.65 | 46.25 ± 143.68 | | | 162467.03 ± 95635.75 | 162464.18 ± 95635.75 | 162467.13 ± 95635.61 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d65535 (c10) | 4.23 ± 0.17 | 3.96 ± 3.78 | 33.33 ± 1.70 | 11.40 ± 6.84 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d100000 (c1) | 1797.01 ± 0.45 | 1797.01 ± 0.45 | | | 55652.04 ± 13.82 | 55649.19 ± 13.82 | 55653.97 ± 11.53 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d100000 (c1) | 16.06 ± 0.77 | 16.06 ± 0.77 | 26.00 ± 0.82 | 26.00 ± 0.82 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d100000 (c1) | 993.12 ± 2.92 | 993.12 ± 2.92 | | | 2065.05 ± 6.06 | 2062.21 ± 6.06 | 2069.98 ± 9.54 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d100000 (c1) | 16.81 ± 2.27 | 16.81 ± 2.27 | 34.33 ± 13.42 | 34.33 ± 13.42 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d100000 (c2) | 1771.24 ± 3.23 | 1329.29 ± 443.61 | | | 84660.22 ± 28251.59 | 84657.37 ± 28251.59 | 84663.45 ± 28253.76 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d100000 (c2) | 3.92 ± 0.19 | 11.39 ± 9.22 | 38.33 ± 16.05 | 22.33 ± 16.89 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d100000 (c2) | 1133.56 ± 10.73 | 579.91 ± 13.48 | | | 3536.37 ± 82.40 | 3533.52 ± 82.40 | 3537.53 ± 81.82 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d100000 (c2) | 22.37 ± 2.32 | 12.20 ± 2.01 | 34.67 ± 4.50 | 20.50 ± 4.65 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d100000 (c5) | 1758.60 ± 10.58 | 806.28 ± 515.47 | | | 170523.90 ± 80679.31 | 170521.05 ± 80679.31 | 170524.45 ± 80679.49 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d100000 (c5) | 2.27 ± 0.26 | 5.75 ± 6.75 | 29.00 ± 4.55 | 12.62 ± 8.96 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d100000 (c5) | 47.76 ± 6.31 | 21.83 ± 10.79 | | | 123085.23 ± 63080.66 | 123082.39 ± 63080.66 | 123086.28 ± 63079.59 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d100000 (c5) | 3.71 ± 0.84 | 5.22 ± 5.27 | 25.67 ± 0.94 | 11.67 ± 6.21 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_pp @ d100000 (c10) | 1745.99 ± 2.62 | 514.86 ± 466.60 | | | 314879.35 ± 164997.40 | 314876.51 ± 164997.40 | 314879.71 ± 164997.10 | | |
| | poolside/Laguna-S-2.1-NVFP4 | ctx_tg @ d100000 (c10) | 2.19 ± 0.07 | 3.80 ± 4.61 | 28.67 ± 6.65 | 9.31 ± 6.88 | | | | | |
| | poolside/Laguna-S-2.1-NVFP4 | pp2048 @ d100000 (c10) | 35.82 ± 1.67 | 33.79 ± 126.54 | | | 306536.12 ± 172262.86 | 306533.27 ± 172262.86 | 306536.47 ± 172262.82 | | |
| | poolside/Laguna-S-2.1-NVFP4 | tg128 @ d100000 (c10) | 2.30 ± 0.04 | 3.90 ± 4.70 | 30.33 ± 8.50 | 9.83 ± 7.72 | | | | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| export CUTE_DSL_ARCH=sm_121a # arch string for FP4 kernel JIT | |
| export PATH=/usr/local/cuda/bin:$PATH # nvcc for JIT | |
| export MAX_JOBS=4 # cap JIT fan-out; see warning below | |
| source .venv/bin/activate | |
| vllm serve poolside/Laguna-S-2.1-NVFP4 \ | |
| --revision b482b5d57fda6e4e562a652869bde24ba2a57c92 \ | |
| --speculative-config '{"model":"poolside/Laguna-S-2.1-DFlash-NVFP4","num_speculative_tokens":15,"revision":"723794750422b3efbf3a7b3af76dffb4ba035943"}' \ | |
| --enable-auto-tool-choice \ | |
| --tool-call-parser poolside_v1 \ | |
| --reasoning-parser poolside_v1 \ | |
| --override-generation-config '{"temperature":0.7,"top_p":0.95}' \ | |
| --max-num-seqs 32 \ | |
| --max-model-len 262144 \ | |
| --gpu-memory-utilization 0.85 \ | |
| --host 0.0.0.0 \ | |
| --port 8000 | |
| # --load-format dummy |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Python headers: Triton JIT needs them and DGX OS ships without them. | |
| # Without this, the first server start dies in triton/runtime/build.py. | |
| sudo apt install -y python3.12-dev | |
| curl -LsSf https://astral.sh/uv/install.sh | sh | |
| uv venv -p 3.12 | |
| # vLLM 0.25.1 with CUDA-13 torch (aarch64 wheels are on PyPI) | |
| uv pip install -p .venv/ vllm==0.25.1 --torch-backend=cu130 | |
| # FlashInfer nightly trio: without flashinfer-python the NVFP4 path is not | |
| # native; the jit-cache wheel avoids most first-start JIT compilation. | |
| uv pip install -p .venv/ \ | |
| "flashinfer-python==0.6.15.dev20260712" \ | |
| "flashinfer-cubin==0.6.15.dev20260712" \ | |
| "flashinfer-jit-cache==0.6.15.dev20260712" \ | |
| --extra-index-url https://flashinfer.ai/whl/nightly/ \ | |
| --extra-index-url https://flashinfer.ai/whl/nightly/cu130/ \ | |
| --index-strategy unsafe-best-match | |
| hf download poolside/Laguna-S-2.1-NVFP4 --revision b482b5d57fda6e4e562a652869bde24ba2a57c92 | |
| hf download poolside/Laguna-S-2.1-DFlash-NVFP4 --revision 723794750422b3efbf3a7b3af76dffb4ba035943 # 73 GB total |
Author
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Laguna-S-2.1-NVFP4
https://huggingface.co/poolside/Laguna-S-2.1-NVFP4
Setup (one-time)
Serve
Benchmark