Function load_kernel

det/mmdet/models/utils/involution_cuda.py:25–28

(kernel_name, code, **kwargs)

@cupy._util.memoize(for_each_device=True)
def load_kernel(kernel_name, code, **kwargs):
    code = Template(code).substitute(**kwargs)
    kernel_code = cupy.cuda.compile_with_cache(code)
    return kernel_code.get_function(kernel_name)


CUDA_NUM_THREADS = 1024