github michaelfeil/infinity 0.0.76

15 hours ago
  • torch=2.6.0 update - 5-10% faster attention on hopper
    -> previously 2.4.1 -> does no longer work with torch.compile + bettertransformers. We recommend disabling torch.compile for this model class.
  • flash-attn included in docker image for nvidia.

What's Changed

Full Changelog: 0.0.75...0.0.76

Don't miss a new infinity release

NewReleases is sending notifications on new releases.