github ggml-org/llama.cpp b8859
on GitHub

latest releases: b8860, b8861
2 hours ago
Details

TP: fix 0-sized tensor slices, AllReduce fallback (#21808)

  • TP: fix 0-sized tensor slices, AllReduce fallback

  • fix layer structure <-> GPU count aliasing

  • add missing std::fill

  • fix CUDA device set, max ggml ctx size

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Check out latest releases or
releases around ggml-org/llama.cpp b8859

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.

Get notifications