Yahoo! JAPAN

11時間前 -LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.

8時間前 -Prebuilt binaries of llama.cpp libraries and executables for Linux with CUDA or Vulkan, Linux arm64 with CPU, Vulkan, or OpenCL, and WebAssembly.

23時間前 -The main goal of llama.cpp is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in ...

14時間前 -For all llama.cpp Qwen3.8-27B users ! With dspine release from @TencentHunyuan, 27b now runs even faster. Especially for maths and code Speed run result ...

13時間前 -llama.cpp adds MageVL-Cowork support and checks the type and element count of rope_freqs during model loading. Prerelease builds are available for multiple ...

15時間前 -TL;DR. A llama.cpp fork that runs DeepSeek V4.1 Flash 1017 on one home PC by streaming the experts VRAM → RAM → NVMe. Our build is 378 GB with ~2-bit…

11時間前 -Release context. Release on GitHub · Diff vs previous · All llama.cpp releases · Project homepage. Previous release: Previous on Sat, Nov 7, 2026 · 1 day apart.

20時間前 -Choose a release package matching your GPU, OS and backend. The unified Windows packages cover RTX 20 / 30 / 40 / 50 with NInfer and PolyStrata; llama.cpp and ...

16時間前 -llama.cpp answers noul , choice and score questions over a state (text or JSON), pictures, a video, audio clips ...