Terry Cruz Melo issues

Repositories
Issues
Comments

Results 2 issues of


                                            Terry Cruz Melo

RuntimeError: CUDA error: device-side assert triggered when running Llama on multiple gpus

I'm getting the following error when using more than one gpu `python3 -m fastchat.serve.cli --model-name /tmp/cache/vicuna-13b/ --num-gpus 2` I am unsure if this is a problem on my end or...

bug

Update API Version

This pull request includes updates to the `heyoo` library to enhance the reliability of HTTP requests by implementing retry logic and updating the base URLs. Additionally, new tests have been...