Skip to content

v1.12.1: Patch Release

Compare
Choose a tag to compare
@regisss regisss released this 11 Jul 13:51
· 411 commits to main since this release

Fix 1st token latency time measure

Fix for Mixtral

Other

  • Fix for selective seq length test with batch size 1 #1110 @libinta

Full Changelog: v1.12.0...v1.12.1