llama.cpp b10991

hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run ( #28886 ) Website: https://llama.app Attestations:…

hexagon: add back missing contiguous fast-path and hvx_copy_uu for each run ( #28886 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47775478 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled)…

Read the original source — github.com

release · Shared by tscosj

0 comments

No comments yet.