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,

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…