/home/yurenh2/miniconda3/lib/python3.13/site-packages/torch/autograd/graph.py:865: UserWarning: Attempting to run cuBLAS, but there was no current CUDA context! Attempting to set the primary context... (Triggered internally at /pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:330.)
  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
parity: rel_diff=4.48e-01 cos=0.89945102 t_best 20 vs 20
orig: 6.433s (best of 3)
fast: 4.163s (best of 3)
HOLO_FAST_PARITY_DONE