github ggml-org/llama.cpp b7371

latest releases: b7410, b7406, b7405...
2 days ago

Warning

Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)

  • models : fix the attn_factor for mistral3 graphs

  • cont : rework attn_factor correction logic

  • cont : make deepseek2 consistent

  • cont : add TODO

  • cont : special-case DSv2

  • cont : revert Mistral 3 Large changes

  • cont : fix DS2 to use the original attn_factor

  • cont : minor comments

macOS/iOS:

Linux:

Windows:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.