Hello,
I’m getting an invalid chunk size issue during training with multiple GPUs with a single node.
Error Message: malloc_consolidate() invalid chunk size
Can someone please help me?
Thanks,
Sani
Hello,
I’m getting an invalid chunk size issue during training with multiple GPUs with a single node.
Error Message: malloc_consolidate() invalid chunk size
Can someone please help me?
Thanks,
Sani
Hi, please file an issue with an example of how to reproduce the crash, thanks!