Yes, it's not truly deterministic, but setting to 0 still makes it relatively less random
Things happen in parallel and as we known not even something as basic as adding up a bunch of floats is associative. Combining that with the fact that CUDA makes few guarantees about the order your operations will be carried out (at the block level) makes true deterministic behavior unachievable.
I got ChatGPT Code Interpreter to generate an example for me:
a = 0.1
b = 0.2
c = 0.3
result1 = (a + b) + c
result2 = a + (b + c)
(result1, result2, result1 == result2)
(0.6000000000000001, 0.6, False)