fix bug in python benchmark script

[thevishalagarwal]

Bug: if we use random token ids (with flag --use_random_token), decoding and encoding generates a different set of tokens which is not equal to the original set. This changes the number of prompt tokens and generates incorrect result during benchmarking. e.g.

original_tokens = np.random.randint(100, size=(1, 50))
prompt = tokenizer.decode(original_tokens )
new_tokens = tokenizer.encode(prompt)

Earlier the number of tokens was 50 but in new_tokens it may not be 50.

I have removed the step of encoding the prompt again to solve for this but the tokenization latency also need to be removed.
IMO, it is not an important metric as tokenizer is never a bottleneck and this easily resolves the above problem/bug.

Alternatively, if we do not use the --use_random_token, then the default way of generating tokens/prompt is very slow.

[thevishalagarwal]

@baijumeswani Can you please review this? Thanks!