torchchat generate requires network connection, even if models are cached

[malfet]

🐛 Describe the bug

Run python3 torchchat.py generate stories110M on a system with a bad network connection will hang for 90+ sec before it starts generatin anything

Versions

Not sure why pytorch collect_env is of any use here...

[malfet]

This happens while one import torchao.quantization.quant_api

[kirklandsign]

Issue hasn't been updated for 6 months. Please re-open if it's still valid.