llama.cpp · b11913

hexagon: add GGML_HEXAGON_VTCM_SIZE (#31221) * hexagon: add GGML_HEXAGON_VTCM_MB and GGML_HEXAGON_NTHREADS caps Change-Id: Idffe1613c8db6f96aa842d43d1b2efaed45462a8 * hexagon: rename VTCM cap to GGML_HEXAGON_VTCM_SIZE, drop NTHREADS cap Change-Id: If4c5b9ce9fd6b725c3561421c2295d40599d012d * hexagon: make GGML_HEXAGON_VTCM_SIZE an override, accept K/M/G suffixes Change-Id: Ib8eea84c22f24e6d986b37f215e504b046478c2c **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11913/llama-b11913-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/b11913/llama-b

1 个独立来源 · 1 篇报道切换最早在前 ↕

2026-10-27

llama.cpp releases08:19

b11913

hexagon：添加 GGML_HEXAGON_VTCM_SIZE（#31221）* hexagon：添加 GGML_HEXAGON_VTCM_MB 和 GGML_HEXAGON_NTHREADS 限制条件变更 ID：Idffe1613c8db6f96aa842d43d1b2efaed45462a8 * hexagon：将 VTCM 限制条件重命名为 GGML_HEXAGON_VTCM_SIZE，移除 NTHREADS 限制条件变更 ID：If4c5b9ce9fd6b725c3561421c2295d40599d012d * hexagon：使 GGML_HEXAGON_VTCM_SIZE 成为可覆盖项，并支持 K/M/G 后缀变更 ID：Ib8eea84c22f24e6d986b37f215e504b046478c2c **网站：** - **证明文件：** - **macOS/iOS：** - [macOS Apple Silicon（arm64）](https://github.com/ggml-org/llama.cpp/releases/download/b11913/llama-b11913-bin-macos-arm64.tar.gz) - macOS Apple Silicon（arm64，启用 KleidiAI）[已禁用](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel（x64）](https://github.com/ggml-org/llama.cpp/releases/download/b11913/llama-b)

事件进展与其他报道