| { | |
| "implementation": "gptoss_results", | |
| "config": { | |
| "warmup": 10, | |
| "iters": 50, | |
| "device": "cuda", | |
| "dtype": "torch.float32", | |
| "tokens": 100, | |
| "vary_inputs": true | |
| }, | |
| "stats": { | |
| "avg_ms": 46.913985819956, | |
| "min_ms": 40.44806400088419, | |
| "max_ms": 51.07520399997156, | |
| "std_ms": 2.9921332618008196, | |
| "p50_ms": 47.418902999652346, | |
| "p95_ms": 50.800493049837314, | |
| "p99_ms": 50.948625239852845, | |
| "num_iters": 50, | |
| "tokens_per_s": 2131.560519794133, | |
| "throughput_variance": 139.93911554997217 | |
| }, | |
| "output_sum": 11.53223705291748 | |
| } |