def benchmark()

in 2-dl-container/Container-Root/job/bert/direct_benchmark-gpu.py [0:0]

• 16 lines of code
• 7 McCabe index (conditional complexity)

def benchmark(num_models, num_threads, num_requests, model_file, torchscript=True):
    # Load a model into each NeuronCore
    print('Loading Models To Memory')
    models = [load_model(model_file, torchscript) for _ in range(num_models)]
    tokenizers = [tokenizer for _ in range(num_models)]
    print('Starting benchmark')
    output_list = []
    begin = time.time()
    futures = []
    # Submit all tasks and wait for them to finish
    # https://stackoverflow.com/questions/51601756/use-tqdm-with-concurrent-futures
    with tqdm(total=num_requests) as pbar:
        with ThreadPoolExecutor(num_threads) as pool:
            for i in range(num_requests):
                # futures.append(pool.submit(task, models[i % len(models)], tokenizers[i % len(models)], random.choice(sequence_list)))
                futures.append(pool.submit(task, models[i % len(models)], random.choice(encoded_input_list)))
                # output_list.append(output.result())
            for _ in concurrent.futures.as_completed(futures):
                pbar.update(1)

    test_time = time.time() - begin

    # return test_time, np.array(output_list)
    return test_time