llama.cpp · b11918

opencl: initial support for q3_k (#31172) * opencl: add q3_k AOS mv * opencl: add q3_k SOA mv and tiled mm * opencl: add q3_k noshuffle gemm/gemv for adreno * opencl: add q3_k dp4a gemm for adreno Co-authored-by: Hongqiang Wang * opencl: tune q3_k kernels for adreno Co-authored-by: Hongqiang Wang --------- Co-authored-by: Hongqiang Wang **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11918/llama-b11918-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/b11918/llama-b11918-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/ll

1 个独立来源 · 1 篇报道切换最早在前 ↕

2026-10-27

llama.cpp releases15:22

b11918

opencl：首次支持 q3_k (#31172) * opencl：添加 q3_k AOS 移动 * opencl：添加 q3_k SOA 移动及分块矩阵乘法 * opencl：为 adreno 添加 q3_k 无混洗 gemm/gemv * opencl：为 adreno 添加 q3_k dp4a gemm 共同作者：王洪强 * opencl：针对 adreno 调优 q3_k 内核共同作者：王洪强 --------- 共同作者：王洪强 **网站：** - **证明文件：** - **macOS/iOS：** - [macOS 苹果芯片（arm64）](https://github.com/ggml-org/llama.cpp/releases/download/b11918/llama-b11918-bin-macos-arm64.tar.gz) - macOS 苹果芯片（arm64，启用 KleidiAI）[已禁用](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS 英特尔（x64）](https://github.com/ggml-org/llama.cpp/releases/download/b11918/llama-b11918-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/ll)

事件进展与其他报道