diff --git a/README.md b/README.md index dbb032b7f..e71634e1c 100644 --- a/README.md +++ b/README.md @@ -43,40 +43,38 @@ It will include all of the necessary data ================= Benchmark results ================= - perf: items/sec, (sum batchsize) / (elapsed time), higher is better. - peak_memory: MiB - fail n perf sem% std% peak_memory score weight - bert-fp16 0 1 49.82 0.0% 0.2% 23952 49.815508 0.00 - bert-fp32 0 1 20.78 0.0% 0.2% 30922 20.783989 0.00 - bert-tf32 0 1 20.79 0.0% 0.2% 30922 20.787725 0.00 - bert-tf32-fp16 0 1 49.70 0.1% 0.3% 23952 49.697091 3.00 - bf16 0 1 7.91 0.0% 0.1% 1140 7.910341 0.00 - convnext_large-fp16 0 1 123.77 2.5% 13.6% 26632 123.767014 0.00 - convnext_large-fp32 0 1 32.69 0.5% 2.6% 45356 32.687851 0.00 - convnext_large-tf32 0 1 32.64 0.5% 2.6% 45356 32.636185 0.00 - convnext_large-tf32-fp16 0 1 124.93 2.5% 13.4% 26632 124.930007 3.00 - davit_large 0 1 114.54 1.3% 9.8% 32374 114.539282 1.00 - davit_large-multi 0 1 115.18 1.2% 9.3% 32374 115.176873 5.00 - dlrm 0 1 255977.96 0.5% 4.0% 6354 255977.960840 1.00 - focalnet 0 1 151.78 1.6% 12.4% 24098 151.775544 2.00 - fp16 0 1 101.03 0.1% 0.6% 1142 101.025637 0.00 - fp32 0 1 14.42 0.0% 0.2% 1524 14.418942 0.00 - reformer 0 1 10.22 0.0% 0.1% 24756 10.222305 1.00 - regnet_y_128gf 0 1 30.52 0.3% 1.9% 30748 30.518845 2.00 - resnet152 0 1 232.63 1.1% 8.1% 29904 232.629851 1.00 - resnet152-multi 0 1 232.14 1.0% 7.7% 30614 232.144301 5.00 - resnet50 0 1 490.08 2.5% 19.0% 4166 490.076388 1.00 - rwkv 0 1 109.45 0.3% 2.0% 4944 109.449712 1.00 - stargan 0 1 11.40 4.2% 31.9% 35648 11.399463 1.00 - super-slomo 0 1 11.46 0.1% 0.5% 36364 11.463760 1.00 - t5 0 1 13.91 0.6% 4.5% 34794 13.913109 2.00 - tf32 0 1 14.43 0.0% 0.2% 1524 14.430707 0.00 - whisper 0 1 81.71 0.1% 0.6% 35968 81.705971 1.00 - + fail n perf sem% std% peak_memory score weight + bert-fp16 0 8 155.08 0.3% 4.3% 24552 1241.260310 0.00 + bert-fp32 0 8 29.52 0.0% 0.5% 31524 236.337218 0.00 + bert-tf32 0 8 120.46 0.4% 6.1% 31524 964.713297 0.00 + bert-tf32-fp16 0 8 154.76 0.3% 4.1% 24552 1238.477257 3.00 + convnext_large-fp16 0 8 337.48 0.9% 14.0% 27658 2741.604444 0.00 + convnext_large-fp32 0 8 44.61 0.8% 12.6% 49786 354.207225 0.00 + convnext_large-tf32 0 8 135.99 0.7% 11.2% 49786 1089.394916 0.00 + convnext_large-tf32-fp16 0 8 338.58 0.8% 13.0% 27658 2744.325170 3.00 + davit_large 0 8 312.79 0.3% 6.7% 35058 2515.326450 1.00 + davit_large-multi 0 1 2401.65 1.0% 7.7% 42232 2401.651720 5.00 + dlrm 0 1 188777.20 1.8% 14.0% 3194 188777.203190 1.00 + focalnet 0 8 400.47 0.2% 5.4% 26604 3215.431924 2.00 + opt-1_3b 0 1 26.71 0.1% 0.4% 44116 26.714365 5.00 + opt-1_3b-multinode 0 2 34.62 0.2% 1.0% 43552 34.618292 10.00 + opt-6_7b 0 1 14.32 0.0% 0.1% 55750 14.319587 5.00 + opt-6_7b-multinode 0 2 10.79 0.1% 0.7% 49380 10.792595 10.00 + reformer 0 8 61.70 0.0% 0.9% 25376 494.110834 1.00 + regnet_y_128gf 0 8 99.96 0.2% 5.0% 31840 803.012507 2.00 + resnet152 0 8 710.18 0.3% 6.2% 36732 5710.828608 1.00 + resnet152-multi 0 1 5367.34 1.0% 8.1% 38638 5367.338469 5.00 + resnet50 0 8 984.43 0.9% 19.1% 5026 7927.257351 1.00 + rwkv 0 8 428.65 0.2% 3.8% 5546 3435.097716 1.00 + stargan 0 8 51.32 1.8% 40.8% 37848 413.238870 1.00 + super-slomo 0 8 41.63 0.1% 2.3% 34082 332.395065 1.00 + t5 0 8 48.05 0.2% 3.9% 35466 384.317023 2.00 + whisper 0 8 248.16 0.0% 0.6% 37006 1985.861017 1.00 + Scores ------ - Failure rate: 0.00% (OK) - Score: 10.68 + Failure rate: 0.00% (PASS) + Score: 219.06 ## Details