()
| 61 | current = dict(meta, **config.kwargs) |
| 62 | |
| 63 | def kernel_call(): |
| 64 | if config.pre_hook: |
| 65 | config.pre_hook(self.nargs) |
| 66 | self.hook(args) |
| 67 | self.fn.run(*args, num_warps=config.num_warps, num_stages=config.num_stages, **current) |
| 68 | try: |
| 69 | # In testings using only 40 reps seems to be close enough and it appears to be what PyTorch uses |
| 70 | # PyTorch also sets fast_flush to True, but I didn't see any speedup so I'll leave the default |