ggml-org /
llama.cpp
LLM inference in C/C++
Updated 42 min ago
Why now
Version v0.8.0 came out on October 28.
+786 stars gained this week
Stars gained each day, last 30 days
Usual pace · 115 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
It runs on Apple silicon, x86, RISC-V and NVIDIA, AMD, Moore Threads or Vulkan GPUs, with quantized models and CPU+GPU hybrid inference. Install via Docker, prebuilt binaries or building from source.
Summary written by AI from the repository’s description and README.
ggml-org / llama.cpp
View on GitHub(opens in new tab)