Skip to content

llamafile v0.8.8
Compare
Choose a tag to compare
@jart jart released this 29 Jun 18:42
· 17 commits to main since this release
0.8.8
571b4e5
This commit was signed with the committer’s verified signature.
jart Justine Tunney
GPG key ID: 52965314629936D4
Learn about vigilant mode.
  • 571b4e5 Fix bug preventing GPU extraction on Windows
  • 4aea606 Support flash attention in --server mode
  • 7fd9101 Don't flush bf16 subnormals to zero
  • 7692b85 Add Google Gemma v2 support
  • 72fb8ca Introduce --special flag
Assets 4
Loading