lxysl

I seem to have encountered this issue before, but at that time, I was working with vita-1.5, as I am not a developer for vita-1.0. The problem likely lies in...

I am curious why the devices are `cpu` and `cuda:0` instead of `cuda:0` and `cuda:1`. Can you just give this command a try? ```sh CUDA_VISIBLE_DEVICES=0,1 python run.py --data MMBench_TEST_EN_V11 MMBench_TEST_CN_V11...

I checked and confirmed that in the `config.json` file of the vita-1.0 repository on Hugging Face, there is a `model_type` param：https://huggingface.co/VITA-MLLM/VITA/blob/main/VITA_ckpt/config.json

Does this mean that the plugin is no longer compitable with quick look on macOS Sequoia, no matter how modified?

感谢您的反馈，我们正在复现这个问题。

我们发现这可能是由于数值溢出造成的，改为 torch.bfloat16 可以初步解决。 参考：https://github.com/huggingface/transformers/issues/35393 和 https://github.com/huggingface/transformers/issues/35270 以下提供一个示例代码。 ```python import argparse import os import time import numpy as np import torch from PIL import Image from decord import VideoReader, cpu from...

最新版本已支持指定双卡

mac版 2.15.5 也同样无法同步，webdav 和 upstash 都不行。