github ggml-org/llama.cpp b7444

latest releases: b9159, b9158, b9156...
4 months 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.

Details

ggml : use WARP_SIZE/2 for argmax reduction offset (#18092)

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.