github ggml-org/llama.cpp b7398

latest releases: b7423, b7422, b7418...
one day 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.

vulkan: Fix data race/hang in scalar/cm1 flash attention (#17887)

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.