Skip to content

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc. #6583

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc.

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc. #6583

The logs for this run have expired and are no longer available.