加入
KernelBench operators
Faster GPU kernels for PyTorch operators, exactly as correct as the reference (placeholder)
| 1 | { |
| 2 | "domain": "computer-science", |
| 3 | "image": "python:3.12-slim", |
| 4 | "data": "The twelve problems and their input shapes are in problems/; nothing else is needed.", |
| 5 | "benchmark": { |
| 6 | "task": "GPU kernel optimization", |
| 7 | "metric": { |
| 8 | "name": "speed-up", |
| 9 | "better": "higher" |
| 10 | }, |
| 11 | "subtasks": "kernels", |
| 12 | "guardrails": [ |
| 13 | "Outputs match the PyTorch reference within atol 1e-2 and rtol 1e-2 on five random inputs", |
| 14 | "Timed on the pinned H100 runner, the median of 100 runs after warm-up", |
| 15 | "No library calls the reference does not make" |
| 16 | ], |
| 17 | "aggregate": "geomean", |
| 18 | "baseline": { |
| 19 | "name": "PyTorch eager", |
| 20 | "score": 1, |
| 21 | "subtasks": { |
| 22 | "matmul": 1, |
| 23 | "conv2d": 1, |
| 24 | "softmax": 1, |
| 25 | "layernorm": 1, |
| 26 | "gelu": 1, |
| 27 | "attention": 1, |
| 28 | "groupnorm": 1, |
| 29 | "maxpool": 1, |
| 30 | "cumsum": 1, |
| 31 | "argmax": 1, |
| 32 | "mse-loss": 1, |
| 33 | "lstm-cell": 1 |
| 34 | } |
| 35 | } |
| 36 | } |
| 37 | } |