Local Ai
b9275
Release b9275 of llama.cpp includes optimization of the Metal concat kernel and fixes to the GGML_OP_SET kernel threads . The release extends test coverage for copy operations with different source an
Release b9275 of llama.cpp includes optimization of the Metal concat kernel and fixes to the GGML_OP_SET kernel threads . The release extends test coverage for copy operations with different source and destination tensor shapes, adding 50 new reshaping test cases covering 1D-2D-3D-4D conversions . Additional improvements include Metal concat kernel optimizations with row batching for small widths and a bug fix for a dangling reference issue .
Source: llama.cpp Releases | 2026-05-21