INNER CODE UNIT · Python
decode_seconds
invergent-ai/surogate · surogate/serve/tools/reference/qwen3_5/cli.py:382
decode_seconds = time.perf_counter() - decode_started
generated_text = frontend.decode(generated, skip_special_tokens=True)
stop_reason = (
"disabled"
if args.decode == 0
else "stop_token"
if generated and generated[-1] in stops
else "length"
)
_print_result(
prompt=prompt,
generated=generated,
generated_text=generated_text,
stop_reason=stop_reason,
timings=Timings(
load_seconds,
preprocess_seconds,