github ggml-org/llama.cpp b7673

latest releases: b7699, b7698, b7697...
2 days ago
Details

metal : add MoE kernel specialization for ne20=5 (#18667)

Add template specialization for kernel_mul_mm_id_map0 with ne20=5
to support models using 5 active experts (e.g., VAETKI).

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.