llama.cpp

LLM inference in C/C++ with quantization — runs models on CPU, GPU, and edge devices.

Bintang

133,692

Fork

25,250

Bahasa

C++

Kategori

Inference & Serving

Dapatkan kode

# Clone repositori
git clone https://github.com/ggml-org/llama.cpp

Apa itu llama.cpp?

LLM inference in C/C++ with quantization — runs models on CPU, GPU, and edge devices.

Apakah llama.cpp aman digunakan?

llama.cpp adalah proyek open source dari ggml-org di GitHub. Tinjau kode sumber dan lisensi sebelum menggunakannya di produksi.

Bagaimana memulai dengan llama.cpp?

git clone https://github.com/ggml-org/llama.cpp

llama.cpp ditulis dalam bahasa apa?

openSource.faqWhatLanguageAnswer

Run large models locally with a single command — LLMs, vision, and embeddings on any machine.

High-throughput, memory-efficient inference and serving engine for LLMs with PagedAttention.

AI gateway to call 100+ LLM APIs in OpenAI format with cost tracking, guardrails, and load balancing.