| { | |
| "implementation": "gptoss_results", | |
| "config": { | |
| "warmup": 10, | |
| "iters": 50, | |
| "device": "cuda", | |
| "dtype": "torch.float32", | |
| "tokens": 100, | |
| "vary_inputs": true | |
| }, | |
| "stats": { | |
| "avg_ms": 45.94982444000152, | |
| "min_ms": 40.76497799997014, | |
| "max_ms": 52.299967999942965, | |
| "std_ms": 3.623045351544196, | |
| "p50_ms": 45.46925300002158, | |
| "p95_ms": 51.35251775002985, | |
| "p99_ms": 52.12179027996967, | |
| "num_iters": 50, | |
| "tokens_per_s": 2176.286878540176, | |
| "throughput_variance": 169.79505096491204 | |
| }, | |
| "output_sum": 11.53223705291748 | |
| } |