Jinxing Pan

优雅关闭的逻辑好像写错了

2

这部分好像逻辑写错了,进程结束才break才对 

Thanks for the great work! I wonder if this loader can work with DistributedSampler? Or how can I use it such that it can work like a pytorch dataloader with...

Add weights_only=True in torch.load

5

FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary...

Op_builder->is_compatible quite warning

1

Set the default value of op_builder/xxx.py/is_compatible()/verbose to False for quite warning. Add verbose judgement before op_builder/xxx.py/is_compatible()/self.warning(...). Otherwise the verbose arg will not work.

Different evaluate result between different VLMEvalKit version

8

The official LLaVA-v1.5-7B model gets 1362 points in MME Perception scores under the newest code 69b7b5e.  But it turns out to be 1497 under the 027e38c8df0c312135da70a2abf68fe706b05629 commit.  I...