cktlco
cktlco
Based on the OP's suggestion, I was able to resolve exactly the same issue by specifying the `vila-1.5-13b-w4-g128-awq-v2.pt` file location (not just the `llm/` directory) directly in the `--quant-path` param....
The generated video is great, by the way -- keep up the good work! https://github.com/user-attachments/assets/047d3340-5e01-4120-a247-e76668a1703d
Yes, setting this environment variable before running solved it for me: ``` PYTORCH_CUDA_ALLOC_CONF=exandable_segments:True ``` and I see it using a little over 20GB with that setting with nvidia-smi: ``` 20423MiB...
Great job!
> I think I disagree with the DAN idea. Of we continue this reasoning a little, Dan really should go in jailbreaks, and jailbreaks is not a meaningful category (too...