# Regular BF16 GEMM (what you normally do)
reference = lhs @ rhs.t()  # Standard PyTorch GEMM

# Check memory usage
bf16_memory = lhs.numel() * 2 + rhs.numel() * 2  # 2 bytes per BF16
fp8_memory = lhs.numel() * 1 + rhs.numel() * 1   # 1 byte per FP8

print(f"BF16 memory: {bf16_memory / 1024**2:.1f} MB")
print(f"FP8 memory: {fp8_memory / 1024**2:.1f} MB")
print(f"Memory saved: {(1 - fp8_memory/bf16_memory)*100:.1f}%")