github ggml-org/llama.cpp b9580

latest release: b9581
4 hours ago
Details

vulkan: add v_dot2_f32_f16 support in matrix-matrix multiplication and Flash Attention (#24123)

  • vulkan: add support for valve fp16 dot2 extension

  • use macro for dot2 path choice

  • properly check for the feature

  • add dot_product abstraction to reduce preprocessor branching

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.