📖 项目简介
C++ 实现的高性能 LLM 推理引擎，支持在消费级硬件上运行大模型。
🔗 GitHub 项目地址
https://github.com/ggerganov/llama.cpp
🔄 可替代的商用软件
OpenAI API
📝 项目原文介绍（英文）
llama.cpp LLM inference in C/C++ ggml / ops / maintainer PRs%20sort%3Aupdated-desc) / dev stats / lib llama API / llama-server REST API Quick start A few options to get llama.cpp installed on your machine: - Visit and follow the instructions - Run with Docker - see our Docker documentation - Download pre-built binaries from the releases page - Build from source by cloning this repository - check out our build guide Once installed: sh Download and run a model directly from Hugging Face llama cli
💬 社区讨论
📌 Reproducible LLM Inference on Qualcomm HTP v81 (SM8850): Scheduler, Quantization, Memory, GPU/HTP Offload and MTP — 由 gat45 发布于 2026-08-30
📌 Numerical gap between 1-token and block decode ('verification' in DFlash) can flip greedy argmax — 由 oftrongs 发布于 2026-08-30
📌 How disabling prefetching should be implemented? — 由 Nekotekina 发布于 2026-08-30
📌 Make an --autotune flag for available model, hardware *and* user priorities? — 由 dagbdagb 发布于 2026-08-30
📌 RFC: Metal cooperative cancellation for abort callbacks — 由 QuintinShaw 发布于 2026-08-30