llama.cpp releases · · 1 min read

b10975: cuda : enable i16 and i32 for DUP (#28897)

Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.

  • cuda : enable i16 and i32 for DUP

  • docs : update ops table for DUP on CUDA

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from llama.cpp releases