Function bounded_parallel_map

tokenizer/convert/convert.py:902–934

Parallel map, but with backpressure. If the caller doesn't call `next` fast enough, this will stop calling `func` at some point rather than letting results pile up in memory. Specifically, there is a max of one output value buffered per thread.

(func: Callable[[In], Out], iterable: Iterable[In], concurrency: int, max_workers: int | None = None, use_processpool_executor: bool = False)

def bounded_parallel_map(func: Callable[[In], Out], iterable: Iterable[In], concurrency: int, max_workers: int | None = None, use_processpool_executor: bool = False) -> Iterable[Out]:
    '''Parallel map, but with backpressure.  If the caller doesn't call `next`
    fast enough, this will stop calling `func` at some point rather than
    letting results pile up in memory.  Specifically, there is a max of one
    output value buffered per thread.'''
    if concurrency < 2:
        yield from map(func, iterable)
        # Not reached.
    iterable = iter(iterable)
    executor_class: type[ThreadPoolExecutor] | type[ProcessPoolExecutor]
    if use_processpool_executor:
        executor_class = ProcessPoolExecutor
    else:
        executor_class = ThreadPoolExecutor
    with executor_class(max_workers=max_workers) as executor:
        futures: list[concurrent.futures.Future[Out]] = []
        done = False
        for _ in range(concurrency):
            try:
                futures.append(executor.submit(func, next(iterable)))
            except StopIteration:
                done = True
                break

        while futures:
            result = futures.pop(0).result()
            while not done and len(futures) < concurrency:
                try:
                    futures.append(executor.submit(func, next(iterable)))
                except StopIteration:
                    done = True
                    break
            yield result


def check_vocab_size(params: Params, vocab: Vocab, pad_vocab: bool = False) -> None: