llama.cpp · b11981

hexagon: improve DDR bw utilization in transposed CONCAT (#31277) * hex-concat: double row block size for transposed CONCAT * hex-concat: double buffer scratchpads * hex-concat: chunked src1 rows in transposed concat * hex-concat: pad src1 VTCM stride to spread gather lanes * hex-vgather: apply similar vgather opts to SSM_CONV and GDN --------- Co-authored-by: Max Krasnyansky **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11981/llama-b11981-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11981/llama-b11981-bin-macos-x64.tar.gz) - [iOS XCF