|
| 1 | +graph-net-test-compiler-log [Processing] /work/GraphNet/samples/transformers-auto-model/hf-tiny-model-private_tiny-random-BlipModel |
| 2 | +graph-net-test-compiler-log [Config] model: hf-tiny-model-private/tiny-random-BlipModel |
| 3 | +graph-net-test-compiler-log [Config] device: cuda |
| 4 | +graph-net-test-compiler-log [Config] hardware: NVIDIA A100-SXM4-80GB |
| 5 | +graph-net-test-compiler-log [Config] compiler: inductor |
| 6 | +graph-net-test-compiler-log [Config] warmup: 5 |
| 7 | +graph-net-test-compiler-log [Config] trials: 20 |
| 8 | +graph-net-test-compiler-log [Config] compile_framework_version: 2.7.1+cu126 |
| 9 | +[Profiling] Using device: cuda NVIDIA A100-SXM4-80GB, warm up 5, trials 20 |
| 10 | +Trial 1: e2e=6.64949 ms, gpu=6.46451 ms |
| 11 | +Trial 2: e2e=6.58774 ms, gpu=6.47782 ms |
| 12 | +Trial 3: e2e=6.57296 ms, gpu=6.47270 ms |
| 13 | +Trial 4: e2e=6.59156 ms, gpu=6.47782 ms |
| 14 | +Trial 5: e2e=6.53505 ms, gpu=6.43277 ms |
| 15 | +Trial 6: e2e=6.50096 ms, gpu=6.40000 ms |
| 16 | +Trial 7: e2e=6.55699 ms, gpu=6.45632 ms |
| 17 | +Trial 8: e2e=8.09932 ms, gpu=7.97901 ms |
| 18 | +Trial 9: e2e=8.67844 ms, gpu=8.54016 ms |
| 19 | +Trial 10: e2e=9.74393 ms, gpu=9.60102 ms |
| 20 | +Trial 11: e2e=9.88483 ms, gpu=9.73722 ms |
| 21 | +Trial 12: e2e=7.18832 ms, gpu=7.06867 ms |
| 22 | +Trial 13: e2e=6.62160 ms, gpu=6.51571 ms |
| 23 | +Trial 14: e2e=6.54459 ms, gpu=6.43482 ms |
| 24 | +Trial 15: e2e=6.50930 ms, gpu=6.40819 ms |
| 25 | +Trial 16: e2e=6.50382 ms, gpu=6.40410 ms |
| 26 | +Trial 17: e2e=7.00188 ms, gpu=6.89766 ms |
| 27 | +Trial 18: e2e=6.83117 ms, gpu=6.72461 ms |
| 28 | +Trial 19: e2e=6.63400 ms, gpu=6.51878 ms |
| 29 | +Trial 20: e2e=6.61588 ms, gpu=6.51059 ms |
| 30 | +[Profiling] Using device: cuda NVIDIA A100-SXM4-80GB, warm up 5, trials 20 |
| 31 | +Trial 1: e2e=3.27635 ms, gpu=3.16826 ms |
| 32 | +Trial 2: e2e=3.16405 ms, gpu=3.07814 ms |
| 33 | +Trial 3: e2e=3.12924 ms, gpu=3.04947 ms |
| 34 | +Trial 4: e2e=3.09730 ms, gpu=3.02285 ms |
| 35 | +Trial 5: e2e=3.04723 ms, gpu=2.97267 ms |
| 36 | +Trial 6: e2e=3.06034 ms, gpu=2.98598 ms |
| 37 | +Trial 7: e2e=3.05533 ms, gpu=2.98086 ms |
| 38 | +Trial 8: e2e=3.02792 ms, gpu=2.95526 ms |
| 39 | +Trial 9: e2e=3.03411 ms, gpu=2.96346 ms |
| 40 | +Trial 10: e2e=2.95377 ms, gpu=2.88563 ms |
| 41 | +Trial 11: e2e=2.94375 ms, gpu=2.87642 ms |
| 42 | +Trial 12: e2e=2.94924 ms, gpu=2.88154 ms |
| 43 | +Trial 13: e2e=2.93207 ms, gpu=2.86413 ms |
| 44 | +Trial 14: e2e=2.91133 ms, gpu=2.84467 ms |
| 45 | +Trial 15: e2e=2.89869 ms, gpu=2.82214 ms |
| 46 | +Trial 16: e2e=2.88749 ms, gpu=2.82112 ms |
| 47 | +Trial 17: e2e=2.88129 ms, gpu=2.81293 ms |
| 48 | +Trial 18: e2e=2.91824 ms, gpu=2.83648 ms |
| 49 | +Trial 19: e2e=2.90084 ms, gpu=2.83238 ms |
| 50 | +Trial 20: e2e=2.89059 ms, gpu=2.82419 ms |
| 51 | +graph-net-test-compiler-log [Datatype][eager]: float32 float32 float32 float32 float32 float32 float32 float32 |
| 52 | +graph-net-test-compiler-log [Datatype][compiled]: float32 float32 float32 float32 float32 float32 float32 float32 |
| 53 | +graph-net-test-compiler-log [DataType] eager:['float32', 'float32', 'float32', 'float32', 'float32', 'float32', 'float32', 'float32'] compiled:['float32', 'float32', 'float32', 'float32', 'float32', 'float32', 'float32', 'float32'] match:True |
| 54 | +graph-net-test-compiler-log [Correctness][equal]: 1 1 0 0 0 0 0 0 |
| 55 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-10_rtol_1.00E-06]: 1 1 0 0 0 0 0 0 |
| 56 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-10_rtol_2.56E-04]: 1 1 1 1 0 0 1 0 |
| 57 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-10_rtol_1.69E-12]: 1 1 0 0 0 0 0 0 |
| 58 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-14_rtol_1.00E-14]: 1 1 0 0 0 0 0 0 |
| 59 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-09_rtol_3.98E-06]: 1 1 0 0 0 0 1 0 |
| 60 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-09_rtol_5.85E-04]: 1 1 1 1 0 0 1 0 |
| 61 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-09_rtol_2.54E-11]: 1 1 0 0 0 0 0 0 |
| 62 | +graph-net-test-compiler-log [Correctness][all_close_atol_2.51E-13_rtol_2.51E-13]: 1 1 0 0 0 0 0 0 |
| 63 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-08_rtol_1.58E-05]: 1 1 1 1 0 0 1 0 |
| 64 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-08_rtol_1.34E-03]: 1 1 1 1 0 0 1 0 |
| 65 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-08_rtol_3.82E-10]: 1 1 0 1 0 0 0 0 |
| 66 | +graph-net-test-compiler-log [Correctness][all_close_atol_6.31E-12_rtol_6.31E-12]: 1 1 0 0 0 0 0 0 |
| 67 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-07_rtol_6.31E-05]: 1 1 1 1 0 0 1 0 |
| 68 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-07_rtol_3.06E-03]: 1 1 1 1 0 0 1 0 |
| 69 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-07_rtol_5.75E-09]: 1 1 0 1 0 0 1 0 |
| 70 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.58E-10_rtol_1.58E-10]: 1 1 0 0 0 0 0 0 |
| 71 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-06_rtol_2.51E-04]: 1 1 1 1 0 0 1 0 |
| 72 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-06_rtol_7.00E-03]: 1 1 1 1 0 0 1 0 |
| 73 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-06_rtol_8.65E-08]: 1 1 1 1 0 0 1 0 |
| 74 | +graph-net-test-compiler-log [Correctness][all_close_atol_3.98E-09_rtol_3.98E-09]: 1 1 0 0 0 0 0 0 |
| 75 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-05_rtol_1.00E-03]: 1 1 1 1 0 0 1 0 |
| 76 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-05_rtol_1.60E-02]: 1 1 1 1 0 0 1 0 |
| 77 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-05_rtol_1.30E-06]: 1 1 1 1 0 0 1 0 |
| 78 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-07_rtol_1.00E-07]: 1 1 0 1 0 0 1 0 |
| 79 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-04_rtol_3.98E-03]: 1 1 1 1 0 0 1 0 |
| 80 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-04_rtol_3.66E-02]: 1 1 1 1 0 0 1 0 |
| 81 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-04_rtol_1.96E-05]: 1 1 1 1 0 0 1 0 |
| 82 | +graph-net-test-compiler-log [Correctness][all_close_atol_2.51E-06_rtol_2.51E-06]: 1 1 1 1 0 0 1 0 |
| 83 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-03_rtol_1.58E-02]: 1 1 1 1 0 0 1 0 |
| 84 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-03_rtol_8.36E-02]: 1 1 1 1 0 0 1 0 |
| 85 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-03_rtol_2.94E-04]: 1 1 1 1 0 0 1 0 |
| 86 | +graph-net-test-compiler-log [Correctness][all_close_atol_6.31E-05_rtol_6.31E-05]: 1 1 1 1 0 0 1 0 |
| 87 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-02_rtol_6.31E-02]: 1 1 1 1 0 0 1 0 |
| 88 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-02_rtol_1.91E-01]: 1 1 1 1 0 0 1 0 |
| 89 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-02_rtol_4.42E-03]: 1 1 1 1 0 0 1 0 |
| 90 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.58E-03_rtol_1.58E-03]: 1 1 1 1 0 0 1 0 |
| 91 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-01_rtol_2.51E-01]: 1 1 1 1 0 0 1 0 |
| 92 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-01_rtol_4.37E-01]: 1 1 1 1 0 0 1 0 |
| 93 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E-01_rtol_6.65E-02]: 1 1 1 1 0 0 1 0 |
| 94 | +graph-net-test-compiler-log [Correctness][all_close_atol_3.98E-02_rtol_3.98E-02]: 1 1 1 1 0 0 1 0 |
| 95 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+00_rtol_1.00E+00]: 1 1 1 1 0 0 1 0 |
| 96 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+00_rtol_1.00E+00]: 1 1 1 1 0 0 1 0 |
| 97 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+00_rtol_1.00E+00]: 1 1 1 1 0 0 1 0 |
| 98 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+00_rtol_1.00E+00]: 1 1 1 1 0 0 1 0 |
| 99 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+01_rtol_3.98E+00]: 1 1 1 1 0 0 1 0 |
| 100 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+01_rtol_2.29E+00]: 1 1 1 1 0 0 1 0 |
| 101 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+01_rtol_1.50E+01]: 1 1 1 1 0 0 1 0 |
| 102 | +graph-net-test-compiler-log [Correctness][all_close_atol_2.51E+01_rtol_2.51E+01]: 1 1 1 1 0 0 1 0 |
| 103 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+02_rtol_1.58E+01]: 1 1 1 1 0 0 1 0 |
| 104 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+02_rtol_5.23E+00]: 1 1 1 1 0 0 1 0 |
| 105 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+02_rtol_2.26E+02]: 1 1 1 1 0 0 1 0 |
| 106 | +graph-net-test-compiler-log [Correctness][all_close_atol_6.31E+02_rtol_6.31E+02]: 1 1 1 1 0 0 1 0 |
| 107 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+03_rtol_6.31E+01]: 1 1 1 1 0 0 1 0 |
| 108 | +grapseth-net-test-compiler-log [Correctness][all_close_atol_1.00E+03_rtol_1.20E+01]: 1 1 1 1 0 0 1 0 |
| 109 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+03_rtol_3.40E+03]: 1 1 1 1 0 0 1 0 |
| 110 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.58E+04_rtol_1.58E+04]: 1 1 1 1 0 0 1 0 |
| 111 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+04_rtol_2.51E+02]: 1 1 1 1 0 0 1 0 |
| 112 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+04_rtol_2.73E+01]: 1 1 1 1 0 0 1 0 |
| 113 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+04_rtol_5.11E+04]: 1 1 1 1 0 0 1 0 |
| 114 | +graph-net-test-compiler-log [Correctness][all_close_atol_3.98E+05_rtol_3.98E+05]: 1 1 1 1 0 0 1 0 |
| 115 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+05_rtol_1.00E+03]: 1 1 1 1 0 0 1 0 |
| 116 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+05_rtol_6.25E+01]: 1 1 1 1 0 0 1 0 |
| 117 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+05_rtol_7.69E+05]: 1 1 1 1 0 0 1 0 |
| 118 | +graph-net-test-compiler-log [Correctness][all_close_atol_1.00E+07_rtol_1.00E+07]: 1 1 1 1 0 0 1 0 |
| 119 | +graph-net-test-compiler-log [Correctness][max_diff]: 0.0 0.0 4.76837158203125e-07 7.450580596923828e-09 nan nan 4.470348358154297e-08 nan |
| 120 | +graph-net-test-compiler-log [Correctness][mean_diff]: 0.0 0.0 8.794346229024086e-08 2.4363089323742315e-09 nan nan 1.3707904145121574e-08 nan |
| 121 | +graph-net-test-compiler-log [Result] status: success |
| 122 | +graph-net-test-compiler-log [Performance][eager]: {"e2e": {"mean": 7.14259, "std": 1.04778, "min": 6.50096, "max": 9.88483}, "gpu": {"mean": 7.02612, "std": 1.03642, "min": 6.4, "max": 9.73722}} |
| 123 | +graph-net-test-compiler-log [Performance][compiled]: {"e2e": {"mean": 2.99796, "std": 0.106326, "min": 2.88129, "max": 3.27635}, "gpu": {"mean": 2.92393, "std": 0.0989045, "min": 2.81293, "max": 3.16826}} |
| 124 | +graph-net-test-compiler-log [Speedup][e2e]: 2.38248 |
| 125 | +graph-net-test-compiler-log [Speedup][gpu]: 2.40297 |
0 commit comments