Skip to content

v3.4.0

Latest
Latest

Choose a tag to compare

View all tags
@jan-grzybek-ampere jan-grzybek-ampere released this 26 Nov 12:51
· 1 commit to main since this release
v3.4.0
9af0385
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Based on ggml-org/llama.cpp b6735 (https://github.com/ggml-org/llama.cpp/releases/tag/b6735)

  • Flash Attention for SWA models fixed
  • New Flash Attention algorithm. It is optimized for long contexts (above 1024). See
    "Flash Attention algorithm selection" section for details how to select attention algorithm
    manually.

Also available at: DockerHub

Assets 4
Loading