FastChat
FastChat copied to clipboard
Add the FixedLengthQueue class, which is used to store a queue with a…
trafficstars
… fixed length and provides a method called contains_stop_sequence to check if the queue contains the given stop sequence.
The clear_torch_cache function is designed to clear GPU memory cache used by the PyTorch library. This can be helpful in reducing memory overhead and avoiding out-of-memory errors when working with large models or datasets.
fix stop_sequence